Offline Reinforcement Learning

Follow this topic Ask about this topic

Momentum

121 papers in the last four weeks, up 267% on the four weeks before. 1.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 778

Jan 26, 2026cs.LG

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates

While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive computational costs and the risk of catastrophic forgetting. We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates. JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly. These estimates are then used to directly modulate the LLM's output logits. We theoretically prove that this additive update rule is the exact closed-form solution to the KL-constrained policy optimization objective. Extensive experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods. Crucially, JitRL outperforms the performance of computationally expensive fine-tuning methods (e.g., WebRL) while reducing monetary costs by over 30 times, offering a scalable path for continual learning agents. The code is available at https://github.com/liushiliushi/JitRL.

Yibo Li, Zijie Lin, Ailin Deng +5

National University of Singapore, Singapore.

Large Language Model Reinforcement Learning Offline Reinforcement Learning Replay-Based Continual Learning Large Language Model Agents Continual Learning Gradient

Jan 17, 2026cs.CL

PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning

Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this preference-driven decision process as calendar conflict resolution. Automating this decision process is crucial yet challenging. Scheduling logistics can drain hours, and human delegation often fails at scale, which motivates us to ask: Can we trust large language models (LLMs) or language agents to manage time? To enable a systematic study of this question, we introduce CalConflictBench, a benchmark for long-horizon calendar conflict resolution. In CalConflictBench, conflicts are presented to agents round-by-round over a calendar year, requiring them to infer and adapt to user preferences progressively. Our experiments show that current LLM agents perform poorly with high error rates, e.g., Qwen-3-30B-Think has an average error rate of 35%. To address this gap, we propose PEARL, a reinforcement-learning framework that (i) augments the language agent with an external preference memory that stores and updates inferred strategies (e.g., attendee priorities, topic importance, time/location preferences), and (ii) optimizes the agent with round-wise rewards that directly supervise decision correctness, ranking quality, and memory usage across rounds. Experiments on CalConflictBench show that PEARL achieves an error reduction rate of 0.76 and a 55% improvement in average error rate compared to the strongest baseline.

Bingxuan Li, Jeonghwan Kim, Cheng Qian +4

University of Illinois at Urbana-Champaign · Viven

Schedule Assistant Offline Reinforcement Learning

Jan 13, 2026cs.RO

Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding

Achieving agile and generalized legged locomotion across terrains requires tight integration of perception and control, especially under occlusions and sparse footholds. Existing methods have demonstrated agility on parkour courses but often rely on end-to-end sensorimotor models with limited generalization and interpretability. By contrast, methods targeting generalized locomotion typically exhibit limited agility and struggle with visual occlusions. We introduce a unified reinforcement learning (RL) framework for agile and generalized locomotion that incorporates a novel attention-based map encoder in the control policy. This encoder extracts local and global mapping features and uses attention mechanisms to focus on salient regions, producing an interpretable and generalized embedding for RL-based control. We further propose a learning-based mapping pipeline that provides fast, uncertainty-aware terrain representations robust to noise and occlusions, serving as policy inputs. It uses neural networks to convert depth observations into local elevations with uncertainties, and fuses them with odometry. The pipeline also integrates with parallel simulation so that we can train controllers with online mapping, aiding sim-to-real transfer. We validate our framework with the proposed mapping pipeline on a quadruped and a biped robot, and the resulting controllers demonstrate strong agility and generalization to unseen terrains in simulation and in real-world experiments.

Chong Zhang, Victor Klemm, Fan Yang +1

1Robotic Systems Lab, ETH Zurich, Switzerland · 2Secure, Reliable, and Intelligent Systems Lab, ETH Zurich, Switzerland · 3ETH AI Center, Switzerland

Agile Locomotion Sensorimotor Experience Offline Reinforcement Learning Digital Elevation Models

Jan 12, 2026cs.CV

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding

While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps humans naturally employ. For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Strategy to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to gradually strengthen exploitation. To train our model, we construct a dataset of 56k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework.

Jianghao Yin, Qingbin Li, Kun Sun +10

East China Normal University · ByteDance

Recent Vision-Language Models Theory-Of-Mind Reasoning Cognitive Science Offline Reinforcement Learning Action Expert

Jan 2, 2026cs.LG

Precision autotuning for linear solvers via contextual bandit-based RL

We propose a reinforcement learning (RL) framework for \xy{responsive} precision tuning for linear solvers, which can be extended to general algorithms. The framework is formulated as a contextual bandit problem and solved using incremental action-value estimation with a discretized state space to select optimal precision configurations for computational steps, \xy{retaining} precision and computational efficiency. To verify its effectiveness, we apply the framework to iterative refinement for solving linear systems

Ax = b

. In this application, our approach dynamically chooses precisions based on calculated features from the system while maintaining acceptable accuracy and convergence. In detail, an action-value estimator takes discretized features (e.g., approximate condition number and matrix norm) as input and outputs estimated action values, from which a policy selects the actions (chosen precision configurations for specific steps), optimized via an

ε

-greedy strategy to maximize a multi-objective reward to balance accuracy and computational cost. Empirical results demonstrate effective precision selection, \xy{increasing the use of lower-precision arithmetic} while maintaining accuracy comparable to double-precision baselines. \xy{We further evaluate the learned policies in a compiled CPU GMRES-IR implementation using FP16, FP32, and FP64 arithmetic for solver-level native validation.} The framework generalizes to diverse out-of-sample data and provides insights into applying RL precision selection to other numerical algorithms, advancing mixed-precision numerical methods in scientific computing. To the best of our knowledge, this is the first work on precision autotuning with RL with verification on unseen datasets.

Erin Carson, Xinye Chen

Charles University Prague, Czech · Sorbonne Université, CNRS, LIP6 Paris, France

Solver Iterations Full-Precision Performance Precision Offline Reinforcement Learning Greedy Algorithm Value Functions

Dec 30, 2025stat.ML

Soft Fitted Q-Iteration without Bellman Completeness: Occupancy Reweighting and Temperature Annealing

Fitted

Q

-iteration (FQI) is a standard regression-based method for optimal control in offline reinforcement learning, but its stability under function approximation often relies on Bellman completeness, which requires Bellman images of the fitted class to remain in the class. We study Kullback--Leibler (KL)-regularized, or soft, FQI relative to a fixed reference policy without this assumption. Our key insight is that soft control locally inherits the contraction of policy evaluation in a discounted-occupancy norm. At the soft-optimal fixed point, the linearization of the soft Bellman operator is exactly the Bellman operator for the soft-optimal policy, which contracts in its discounted-occupancy norm; projection in the same norm preserves this contraction. Standard soft FQI instead projects under the offline state-action distribution and need not preserve this property. Motivated by this observation, we propose \emph{occupancy-reweighted soft FQI}, which retains standard Bellman targets and least-squares updates while reweighting regressions by discounted-occupancy ratios induced by the current soft policy. Under

Q

-function realizability and local regularity, we establish local contraction and finite-sample convergence with estimated ratios, without Bellman completeness. We then use temperature annealing to convert the local result into global convergence from arbitrary initialization: sufficiently high temperature provides a globally contractive starting regime, while gradual cooling connects successive local contraction regions to any prescribed positive target temperature. Under an action-gap margin condition, switching at a fixed positive temperature to hard FQI with refreshed occupancy weights also yields population and finite-sample convergence to the unregularized optimum.

Lars van der Laan, Nathan Kallus

Department of Statistics, University of Washington · Netflix · Cornell University

Entropy Regularized Reinforcement Learning Boltzmann Policies Bellman Equation Offline Reinforcement Learning Annealing Occupancy

Dec 24, 2025cs.LG

Meta-RL with Bayesian Linear Task Models

Deep Bayesian reinforcement learning adapts to unseen tasks by inferring latent transition and reward models, but existing methods typically rely on variational posteriors and evidence lower bounds, introducing approximation error and unstable task representations. We introduce GLiBRL, a deep Bayesian RL framework that combines generalised linear task models with learnable non-linear basis functions. GLiBRL features conjugate Bayesian inference, yielding exact, sequential posterior updates over task parameters and model noise, together with a closed-form marginal likelihood that eliminates variational inference. The update is naturally permutation-invariant, allowing GLiBRL to integrate with both off- and on-policy algorithms. GLiBRL also learns task representation admitting an exact kernel identity, relating distances between task representations to kernel discrepancies over the task contexts. Compared against eight representative or recent meta reinforcement learning methods, GLiBRL achieves the highest aggregate zero-shot test performance on both the MuJoCo locomotion and MetaWorld manipulation benchmarks.

Jingyang You, Hanna Kurniawati

School of Computing Australian National University

Offline Reinforcement Learning Variational Inference

Dec 19, 2025physics.flu-dyn

The HydroGym Reinforcement Learning Platform for Fluid Dynamics

Modeling and controlling fluids is critical across science and engineering. Effective flow control can increase lift, reduce drag, enhance mixing, and attenuate noise, potentially unlocking new technologies. Yet controlling fluids is hard: the dynamics are high-dimensional, nonlinear, and multiscale. While reinforcement learning (RL) has recently succeeded in robotics and protein folding through shared benchmarks, fluid dynamics has resisted such progress: each controller is typically tuned to a single geometry and operating point, making results hard to accumulate, transfer, and compare. We introduce HydroGym, a solver-independent RL platform for flow control, and show that standardized infrastructure unlocks transferable control intelligence across flow regimes. HydroGym provides 61+ validated environments spanning laminar to turbulent flows, with systematic Reynolds number progressions up to Re=400,000 and Mach number variations in 2D and 3D. It supports diverse backends, including finite-volume, spectral-element, finite-element, lattice-Boltzmann, and fully differentiable solvers for gradient-enhanced optimization. Across environments, RL agents consistently discover robust control principles, such as boundary-layer manipulation, acoustic-feedback disruption, and wake reorganization, yielding drag reductions exceeding 90% in canonical configurations. Critically, we demonstrate zero-shot transfer: agents trained only on a simplified channel flow achieve 38% friction-drag reduction on an unseen 3D wing section at chord Reynolds number Re=200,000 reducing exploration costs by four orders of magnitude versus direct on-wing optimization. This suggests RL agents uncover essential physics rather than configuration-specific patterns, pointing toward generalizable control. HydroGym offers extensible, scalable community infrastructure for fluid dynamics, machine learning, and control research.

Christian Lagemann, Sajeda Mokbel, Miro Gondrum +18

Department of Mechanical Engineering, University of Washington, Seattle, WA 98195, United States · AI Institute in Dynamic Systems, University of Washington, Seattle, WA 98195, United States · Chair of Fluid Mechanics and Institute of Aerodynamics, RWTH Aachen University, Aachen, Germany +9

Fluid Dynamics Fluid Controls Reinforcement Learning Control Full-Body Humanoid Control Offline Reinforcement Learning Skillgym

Dec 7, 2025stat.ML

Statistical analysis of Inverse Entropy-regularized Reinforcement Learning

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of the recovered reward: many reward functions can induce the same optimal policy, rendering the inverse problem ill-posed. In this paper, we develop a statistical framework for Inverse Entropy-regularized Reinforcement Learning that resolves this ambiguity by combining entropy regularization with a least-squares reconstruction of the reward from the soft Bellman residual. This combination yields a unique and well-defined so-called least-squares reward consistent with the expert policy. We model the expert demonstrations as a Markov chain with the invariant distribution defined by an unknown expert policy

π^\star

and estimate the policy by a penalized maximum-likelihood procedure over a class of conditional distributions on the action space. We establish high-probability bounds for the excess Kullback--Leibler divergence between the estimated policy and the expert policy, accounting for statistical complexity through covering numbers of the policy class. These results lead to non-asymptotic minimax optimal convergence rates for the least-squares reward function, revealing the interplay between smoothing (entropy regularization), model complexity, and sample size. Our analysis bridges the gap between behavior cloning, inverse reinforcement learning, and modern statistical learning theory.

Denis Belomestny, Alexey Naumov, Artemy Rubtsov +1

Entropy Regularized Reinforcement Learning Offline Reinforcement Learning Reward Functions Optimal Policies Statistical Inference

Dec 6, 2025cs.LG

Auto-exploration for online reinforcement learning

The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient exploration over both state and action spaces. However, this yields non-implementable algorithms and sub-optimal performance. To resolve these limitations, we introduce a new class of methods with auto-exploration, or methods that automatically explore both state and action spaces. Auto-exploration can be applied in both the tabular and linear function approximation setting. Under algorithm-independent assumptions on the existence of an exploring optimal policy, both settings attain

O(ε^{-2})

sample complexity to solve to

ε

error. These complexities are novel since they avoid algorithm-dependent parameters seen in prior works, which may be arbitrarily large. The methods are also simple to implement because they are parameter-free. We achieve these results by integrating auto-exploration into policy mirror descent to avoid the (unknown) stationary distribution seen in prior art. In the tabular setting, we introduce a dynamic exploration time with a data-driven stopping time, while for linear function approximation we propose a new sampling distribution based on the discounted visitation distribution that covers a more general class of Markov chains.

Caleb Ju, Guanghui Lan

Stochastic Exploration Offline Reinforcement Learning Mirror Descent

Nov 25, 2025cs.LG

Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning

The emergence and evolution of feature reliance in deep reinforcement learning agents remain poorly understood. Here, we introduce a methodological framework for analyzing the learning process through quantitative analysis of saliency maps. This approach aggregates saliency information at the object and modality level into hierarchical attention profiles, quantifying how agents allocate attention over time, thereby forming attention trajectories throughout training. These profiles are then compared across controlled conditions, connected to behavioral measurements and reproduced with different saliency methods to assess the robustness of the findings. Applied to Atari 2600 benchmarks, custom Pong environments, and biomechanical user simulations in visuomotor tasks, this framework uncovers algorithm-specific attention biases, diagnosed unintended reward-driven strategies, and overfitting to redundant sensory channels. These patterns correspond to measurable behavioral differences, demonstrating empirical links between attention profiles, learning dynamics, and agent behavior. The results establish attention trajectories as a promising diagnostic axis for tracing how feature reliance develops during training and for identifying biases and vulnerabilities invisible to performance metrics alone.

Charlotte Beylier, Hannah Selder, Arthur Fleig +2

Max Planck Institute for Human Cognitive and Brain Sciences · Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig · Leipzig, Germany +2

Offline Reinforcement Learning Saliency Sensory Feedback Diagnosis

Nov 25, 2025eess.SY

Reinforcement Learning to Initialize Newton-Raphson for AC Power Flow with Quantum Annealing-Based Environment Updates

The Newton-Raphson (NR) method is widely used for solving power flow (PF) equations due to its quadratic convergence. However, its performance deteriorates under poor initialization or extreme operating scenarios, e.g., high levels of renewable energy penetration. We propose the use of reinforcement learning (RL) to optimize the initialization of NR, and introduce a quantum-enhanced RL environment update mechanism that addresses the combinatorially large action space at each RL timestep by formulating the voltage adjustment task as a Quadratic Unconstrained Binary Optimization (QUBO) problem, solved with an Ising machine. RL initialization is benchmarked against flat start and start from the DC (linearized) PF solution on a standard 4-bus system, Iwamoto's ill-conditioned 11-bus system, and the IEEE 118-bus system under normal and stressed loading and reactive power limits, with verified operational solutions. On all systems, a supervised initializer refined by RL requires fewer NR iterations than flat and DC starts and than the same initializer without RL, for all seeds. For example, on the 118-bus system under normal and stressed loading, it reached 2.04 and 2.86 NR iterations, compared with 3.02 and 5.13 from DC start and 2.61 and 3.09 without RL. In wall-clock time, this pays off only for an initializer integrated into the solver and reused for many solves on a fixed topology. On the 4-bus system, a quantum-enhanced RL agent with a quantum-inspired annealer moved challenging initial states that required 29 and 44 NR iterations to initializations that required three NR iterations within one RL timestep.

Zeynab Kaseb, Matthias Moller, Lindsay Spoor +4

Electrical Sustainable Energy, Delft University of Technology, P.O. Box 5031, 2600 GA Delft, The Netherlands. · Applied Mathematics, Delft University of Technology, P.O. Box 5031, 2600 GA Delft, The Netherlands. · Leiden Institute of Advanced Computer Science, Leiden University, P.O. Box 9512, 2300 RA Leiden, The Netherlands. +3

Optimal Power Flow Quantum Annealing Newton Q-Learning Annealing Offline Reinforcement Learning

Nov 12, 2025cs.LG

SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning

Visual reinforcement learning has achieved remarkable progress in visual control and robotics, but its vulnerability to adversarial perturbations remains underexplored. Most existing black-box attacks focus on vector-based or discrete-action RL, and their effectiveness on image-based continuous control is limited by the large action space and excessive environment queries. We propose SEBA, a sample-efficient framework for black-box adversarial attacks on visual RL agents. SEBA integrates a shadow Q model that estimates cumulative rewards under adversarial conditions, a generative adversarial network that produces visually imperceptible perturbations, and a world model that simulates environment dynamics to reduce real-world queries. Through a two-stage iterative training procedure that alternates between learning the shadow model and refining the generator, SEBA achieves strong attack performance while maintaining efficiency. Experiments on MuJoCo and Atari benchmarks show that SEBA significantly reduces cumulative rewards, preserves visual fidelity, and greatly decreases environment interactions compared to prior black-box and white-box methods. The code is available at https://github.com/tairanhuang/seba online.

Tairan Huang, Yulin Jin, Junxu Liu +2

The Hong Kong Polytechnic University Hong Kong, China

Black-Box Adversarial Attacks Offline Reinforcement Learning Visual Fidelity

Nov 4, 2025cs.RO

A Quantitative Comparison of Centralised and Distributed Reinforcement Learning-Based Control for Soft Robotic Arms

This paper presents a quantitative comparison between centralised and distributed multi-agent reinforcement learning (MARL) architectures for controlling a soft robotic arm modelled as a Cosserat rod in simulation. Using PyElastica and the OpenAI Gym interface, we train both a global Proximal Policy Optimisation (PPO) controller and a Multi-Agent PPO (MAPPO) under identical budgets. Both approaches are based on the arm having

n

number of controlled sections. The study systematically varies

n

and evaluates the performance of the arm to reach a fixed target in three scenarios: default baseline condition, recovery from external disturbance, and adaptation to actuator failure. Quantitative metrics used for the evaluation are mean action magnitude, mean final distance, mean episode length, and success rate. The results show that there are no significant benefits of the distributed policy when the number of controlled sections

n\le4

. In very simple systems, when

n\le2

, the centralised policy outperforms the distributed one. When

n

increases to

4< n\le 12

, the distributed policy shows a high sample efficiency. In these systems, distributed policy promotes a stronger success rate, resilience, and robustness under local observability and yields faster convergence given the same sample size. However, centralised policies achieve much higher time efficiency during training as it takes much less time to train the same size of samples. These findings highlight the trade-offs between centralised and distributed policy in reinforcement learning-based control for soft robotic systems and provide actionable design guidance for future sim-to-real transfer in soft rod-like manipulators.

Linxin Hou, Qirui Wu, Zhihang Qin +3

Department of Electrical and Computer Engineering, National University of Singapore · Department of Computer Science, National University of Singapore · Department of Mechanical Engineering, National University of Singapore

Multi-Agent Reinforcement Learning Soft Robotics Offline Reinforcement Learning Cosserat Rod Theory Comparison

Oct 28, 2025cs.RO

Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer

Human demonstrations are widely considered the cornerstone of end-to-end (E2E) autonomous driving despite human demonstration's scarcity for long-tail and safety-critical scenarios. Nonetheless, current E2E autonomous driving (AD) training paradigms continue to rely on human demonstrations. Imitation learning (IL) requires human demonstrations for training, whereas reinforcement learning (RL) has emerged as a promising alternative to reduce this dependency. However, most existing RL methods for E2E AD still rely implicitly on human demonstrations. A pure rewards-based RL method can overcome the need for human demonstrations, but general RL policy gradient methods suffer from the cold-start problem. In this paper, we propose ZTRS (Zero-human demonstration end-to-end autonomous driving with TRajectory Scorer) - a complete RL-based E2E planning paradigm trained solely on real-world images and rule-based rewards, entirely without human demonstration. Through our proposed Exhaustive Policy Optimization (EPO), a policy gradient variant tailored for enumerable trajectory actions and dense supervision, ZTRS enables the model to generalize better to long-tail driving scenarios. We demonstrate this generalization through our SOTA performance against IL approaches on both long-tail Navhard and closed-loop HUGSIM datasets. Project page: https://zhenxinli.net/ZTRS/.

Zhenxin Li, Nadine Chang, Wenhao Yao +9

Institute of Trustworthy Embodied AI, Fudan University · *Work done during an internship at NVIDIA. · NVIDIA +3

Causality-Aware End-To-End Autonomous Driving Autonomous Driving Imitation Learning Offline Reinforcement Learning

Oct 10, 2025cs.CL

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency. Existing solutions to supervise reasoning, such as large-scale Process Reward Models (PRMs), are prohibitively expensive. To address this, we propose CLARity, a cost-effective RL framework that enhances reasoning quality using only a small, general-purpose LLM. CLARity integrates a consistency-aware reward mechanism with a 2-stage refine-then-monitor training pipeline to enhance reasoning consistency, and a dynamic data reformulation strategy to to better exploit limited data. Experiments demonstrate that CLARity improves response consistency by 16.5% and accuracy by 7.5% over baselines. Human evaluations further confirm holistic improvements in coherence and professionalism. Thus, CLARity offers a generalizable solution that enables smaller models to effectively guide expert models by reasoning consistency. Our code is open sourced at: https://github.com/Infinite-set/CLARity

Jiuheng Lin, Cong Jiang, Zirui Wu +2

Wangxuan Institute of Computer Technology, Peking University

Offline Reinforcement Learning

Oct 9, 2025cs.IR

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance

Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of business rules and user queries exposes the inability of existing methods to endow models with robust reasoning capacity for long-tail and challenging cases. Efforts to address this via reinforcement learning strategies like Group Relative Policy Optimization (GRPO) often suffer from sparse terminal rewards, offering insufficient guidance for multi-step reasoning and slowing convergence. To address these challenges, we propose TaoSR-AGRL, an Adaptive Guided Reinforcement Learning framework for LLM-based relevance prediction in Taobao Search Relevance. TaoSR-AGRL introduces two key innovations: (1) Rule-aware Reward Shaping, which decomposes the final relevance judgment into dense, structured rewards aligned with domain-specific relevance criteria; and (2) Adaptive Guided Replay, which identifies low-accuracy rollouts during training and injects targeted ground-truth guidance to steer the policy away from stagnant, rule-violating reasoning patterns toward compliant trajectories. TaoSR-AGRL was evaluated on large-scale real-world datasets and through online side-by-side human evaluations on Taobao Search. It consistently outperforms DPO and standard GRPO baselines in offline experiments, improving relevance accuracy, rule adherence, and training stability. The model trained with TaoSR-AGRL has been successfully deployed in the main search scenario on Taobao, serving hundreds of millions of users.

Jianhui Yang, Yiming Jin, Pengkun Jiao +6

Tsinghua University Beijing, China · Taobao & Tmall Group of Alibaba Beijing, China · Taobao & Tmall Group of Alibaba Hangzhou, China +1

Relevance Agentic Commerce Offline Reinforcement Learning Potential-Based Reward Shaping

Oct 7, 2025cs.LG

The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives

The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforcement Learning (IRL) can infer reward functions from behaviour, existing approaches either produce a single, overconfident reward estimate or fail to address the fundamental ambiguity of the task (non-identifiability). This paper introduces a principled auditing framework that re-frames reward inference from a simple estimation task to a comprehensive process for verification. Our framework leverages Bayesian IRL to not only recover a distribution over objectives but to enable three critical audit capabilities: (i) Quantifying and systematically reducing non-identifiability by demonstrating posterior contraction over sequential rounds of evidence; (ii) Providing actionable, uncertainty-aware diagnostics that expose spurious shortcuts and identify out-of-distribution prompts where the inferred objective cannot be trusted; and (iii) Validating policy-level utility by showing that the refined, low-uncertainty reward can be used directly in RLHF to achieve training dynamics and toxicity reductions comparable to the ground-truth alignment process. Empirically, our framework successfully audits a detoxified LLM, yielding a well-calibrated and interpretable objective that strengthens alignment guarantees. Overall, this work provides a practical toolkit for auditors, safety teams, and regulators to verify what LLMs are truly trying to achieve, moving us toward more trustworthy and accountable AI.

Matthieu Bou, Nyal Patel, Arjun Jagota +2

1Imperial College London · 2Amazon AGI

Large Language Model Alignment Offline Reinforcement Learning Objectives

Oct 2, 2025cs.LG

Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation

Distributionally robust reinforcement learning seeks policies that remain effective when the deployment environment differs from the one that generated the training data. We study model-free robust Q-learning with

χ^2

uncertainty sets and linear function approximation, using data from a single trajectory of an unknown nominal MDP. Evaluating the

χ^2

robust Bellman target introduces the square root of a conditional second moment, which cannot be estimated unbiasedly from one transition, while the projected robust Bellman operator need not be contractive. We address these obstacles through a variational reformulation of the robust Bellman target and a blockwise frozen-target scheme, and establish a finite-time error bound relative to the optimal robust Q-function for every

γ\in(0,1)

. A neural-network experiment illustrates how the variational target can be used in a continuous-state nonlinear-control task.

Saptarshi Mandal, Yashaswini Murthy, R. Srikant

ECE, UIUC · ORIE, UT Austin · ECE, CSL, and the director of NCSA at UIUC

Q-Learning Offline Reinforcement Learning Bellman Equation Finite Time Analysis Convergence

Sep 8, 2025q-bio.NC

Reward function compression facilitates goal-dependent reinforcement learning

Humans can uniquely assign value to novel, abstract outcomes to support reinforcement learning. However, this flexibility is cognitively costly and reduces learning efficiency. We propose that goal-dependent learning initially relies on capacity-limited working memory. With consistent experience, learners create a "compressed" reward function - a simplified goal rule -- that transfers to long-term memory for a more automatic evaluation upon receiving feedback. This automaticity frees working memory resources, thereby boosting learning efficiency. Across six experiments, we demonstrate that learning is impaired by the size of the goal space but improves when this space allows for compression. Additionally, faster reward processing correlates with better learning. Although the algorithmic details remain to be established, our behavioral results and computational models suggest that efficient goal-directed learning relies on compressing complex goal information into a stable reward function. These findings illuminate the cognitive mechanisms of intrinsic motivation and can inform behavioral interventions supporting human goal achievement.

Gaia Molinaro, Anne G. E. Collins

University of California, Berkeley Berkeley, CA 94704

Goal-Conditioned Reinforcement Learning Reward Functions Offline Reinforcement Learning Intrinsic Motivation Working Memory Data Compression Methods+1

Aug 27, 2025cs.AI

ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method - Group Relative Policy Optimization (GRPO) - has achieved critical success, yet it still suffers from the issue of insignificant reward signals. This paper introduces ReST-RL, a unified Reinforced Self-Training (ReST) policy-value framework that reconnects policy optimization and value-guided search to improve LLM reasoning ability. Firstly, ReST-GRPO adopts an optimized ReST-style algorithm to reshape the policy-induced trajectory distribution by increasing the reward variance of GRPO sampling and exposing the policy to more informative partial states, thereby improving training efficiency and effectiveness. Then, we further introduce a decoding optimization method, VM-MCTS, which trains a Value Model (VM) from self-collected Monte-Carlo Tree Search (MCTS) targets and deploys it through an adapted MCTS algorithm to provide precise process signals and verification scores, further enhancing reasoning accuracy. These two stages are internally dependent - ReST-GRPO yields higher-quality trajectories for value learning with VM-MCTS, which in turn enables more effective inference-time search. We validate our framework on multiple coding benchmarks (e.g., APPS, BigCodeBench, and HumanEval), where it significantly outperforms other reinforcement training baselines (naive GRPO, DAPO, and ReST-DPO), as well as decoding and verification baselines (e.g., PRM-BoN and ORM-MCTS), indicating its power to strengthen LLM reasoning capability. Moreover, we further evaluate ReST-RL on out-of-domain math and science reasoning tasks, where it achieves improved performance without target-domain tuning and favorable end-to-end efficiency trade-offs, providing preliminary transfer evidence beyond our primary coding domain.

Sining Zhoubian, Dan Zhang, Jie Tang

Department of Computer Science and Technology, Tsinghua University · Work done when interned at Z.ai. · School of Electronics and Computer Scinence, Univeristy of Southampton

LLM Reasoning Strategies Large Language Model Reinforcement Learning Icr-Rl Offline Reinforcement Learning Flow-Grpo

Aug 22, 2025cs.MA

Integrated Noise and Safety Management in UAM via A Unified Reinforcement Learning Framework

Urban Air Mobility (UAM) envisions the widespread use of small aerial vehicles to transform transportation in dense urban environments. However, UAM faces critical operational challenges, particularly the balance between minimizing noise exposure and maintaining safe separation in low-altitude urban airspace, two potentially conflicting objectives that are often addressed separately. We propose a reinforcement learning (RL)-based air traffic management system that integrates both noise and safety considerations within a unified, decentralized framework. Under this scalable air traffic coordination solution, agents operate in a structured, multi-layered airspace and learn altitude adjustment policies to jointly manage noise impact and separation constraints. The system demonstrates strong performance across both objectives and reveals tradeoffs among separation, noise exposure, and energy efficiency under high traffic density. Among the three objectives, safe separation is accorded the highest priority, whereas the relative significance of noise and energy varies by location and is contingent upon financial and public policy considerations. The findings highlight the potential of RL and multi-objective coordination strategies in enhancing the safety, quietness, and efficiency of UAM operations.

Surya Murthy, Zhenyu Gao, John-Paul Clarke +1

Graduate Research Assistant, Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin · Postdoctoral Fellow, Department of Aerospace Engineering and Engineering Mechanics, The University of Texas at Austin · Professor and Ernest Cockrell, Jr. Memorial Chair in Engineering, Department of Aerospace Engineering and Engineering Mechanics, The University of Texas at Austin +1

Multi-Uav Air Traffic Control Adaptive Coordination Offline Reinforcement Learning

Aug 19, 2025cs.CL

ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs

Interactive medical questioning is essential in clinical consultations, where physicians must actively gather necessary patient information. Yet existing medical Large Language Models (LLMs) predominantly follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details. To bridge this gap, we propose ProMed, a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making. Central to ProMed is the Shapley Information Gain (SIG) reward, which quantifies a question's clinical utility as the amount of newly acquired information, while considering its contextual importance via Shapley values. We integrate SIG into a two-stage training pipeline: (1) SIG-Guided Model Initialization uses Monte Carlo Tree Search to construct high-reward interaction trajectories for supervision, and (2) SIG-Augmented Policy Optimization, with a novel SIG-guided Reward Distribution Mechanism that prioritizes informative questions for fine-grained optimization. Experiments on partial-information medical benchmarks show that ProMed significantly outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm, and generalizes robustly to out-of-domain cases. Our codes are available at https://github.com/hxxding/ProMed.

Hongxin Ding, Baixiang Huang, Yue Fang +8

National Engineering Research Center of Software Engineering, Peking University, China · School of Computing and Data Science, The University of Hong Kong · School of Computer Science, Peking University, Beijing, China +2

Offline Reinforcement Learning

Aug 13, 2025cs.LG

Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with answers per problem, for the answer to be then scored by a reward function. While such RL post-training methods demonstrate significant performance improvements across challenging reasoning domains, the computational cost of generating completions during training with multiple inference steps makes the training cost non-trivial. To address this, we draw inspiration from off-policy RL, and speculative decoding to introduce a novel ReFT framework, dubbed Nested-ReFT, where a subset of layers of the target model acts as the behavior model to generate off-policy completions during training. The behavior model configured with dynamic layer skipping per batch during training decreases the inference cost compared to the standard ReFT frameworks. Our theoretical analysis shows that Nested-ReFT yields unbiased gradient estimates with controlled variance. Our empirical analysis demonstrates improved computational efficiency measured as tokens/sec across multiple math reasoning benchmarks and model sizes. Additionally, we explore three variants of bias mitigation to minimize the off-policyness in the gradient updates that allows for maintaining performance that matches the baseline ReFT performance.

Maxime Heuillet, Yufei Cui, Boxing Chen +2

Universit´e Laval (IID), Canada · Mila - Qu´ebec AI Institute, Canada · Huawei Noah’s Ark Lab (Montreal Research Center), Canada +1

Mathematical Reasoning Benchmarks Large Language Model Fine-Tuning Model Fine-Tuning Offline Reinforcement Learning Reward Functions Code Completion

Jul 26, 2025cs.LG

PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data

Off-policy evaluation (OPE) methods estimate the value of a new reinforcement learning (RL) policy prior to deployment. Recent advances have shown that leveraging auxiliary datasets, such as those synthesized by generative models, can improve the accuracy of OPE methods. Unfortunately, such auxiliary datasets may also be biased, and existing methods for using data augmentation within OPE lack principled uncertainty quantification. In high stakes domains like healthcare, reliable uncertainty estimates are important for ensuring safe and informed deployment of RL policies. In this work, we propose two methods to construct valid confidence intervals for OPE with data augmentation. The first provides a confidence interval over

V^π(s)

, the policy value conditioned on an initial state

s

. To do so we introduce a new conformal prediction method suitable for Markov Decision Processes (MDPs) with continuous state spaces, extending prior work to higher-dimensional settings. Second, we consider the more common task of estimating the average policy performance over all initial states,

V^π

; we introduce a method that draws on ideas from doubly robust estimation and prediction powered inference. Across simulators spanning inventory management, robotics, healthcare, and a real healthcare dataset from MIMIC-IV, we find that our methods can effectively leverage auxiliary data and consistently produce confidence intervals that cover the ground truth policy values, unlike previously proposed methods. Our work enables a future in which OPE can provide rigorous uncertainty estimates for high-stakes domains.

Aishwarya Mandyam, Jason Meng, Ge Gao +4

Stanford University · Gladstone Institutes · Stanford University[cs.LG]

Policy Evaluation Confidence Intervals Offline Reinforcement Learning

Jul 21, 2025cs.AI

RAD: Retrieval High-quality Demonstrations to Enhance Decision-making

Offline reinforcement learning (RL) learns policies from fixed datasets, thereby avoiding costly or unsafe environment interactions. However, its reliance on finite static datasets inherently restricts the ability to generalize beyond the training distribution. Prior solutions based on synthetic data augmentation often fail to generalize to unseen scenarios in the (augmented) dataset. To address these challenges, we propose Retrieval High-quAlity Demonstrations (RAD) for decision-making, which innovatively introduces a retrieval mechanism into offline RL. Specifically, RAD retrieves high-return and reachable states from the offline dataset as target states, and leverages a generative model to generate sub-trajectories conditioned on these targets for planning. Since the targets are high-return states, once the agent reaches such a target, it can continue to obtain high returns by following the associated high-return actions, thereby improving policy generalization. Extensive experiments confirm that RAD achieves competitive or superior performance compared to baselines across diverse benchmarks, validating its effectiveness. Our code is available at https://anonymous.4open.science/r/RAD_0925_1-690E.

Lu Guo, Yixiang Shan, Zhengbang Zhu +5

School of Artificial Intelligence, Jilin University, Changchun, China · School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

Model-Based Reinforcement Learning Offline Reinforcement Learning Improved Generalization Decisions Synthetic Data

Jul 5, 2025cs.AI

A Technical Survey of Reinforcement Learning Techniques for Large Language Models

This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning, and Actor-Critic methods. Additionally, it provides an extensive technical overview of RL techniques specifically tailored for LLMs, including foundational methods like Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), as well as advanced strategies such as Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO). We systematically analyze their applications across domains, i.e., from code generation to tool-augmented reasoning. Crucially, we move beyond descriptive categorization to provide a rigorous algorithmic analysis of failure modes, mathematically framing the structural bottlenecks and stability trade-offs inherent in policy optimization. We also present a comparative taxonomy based on reward modeling, feedback mechanisms, and optimization strategies. Our evaluation highlights key trends. RLHF remains dominant for alignment, and outcome-based RL such as Reinforcement Learning with Verifiable Rewards (RLVR) significantly improves stepwise reasoning. However, persistent challenges such as reward hacking, computational costs, and scalable feedback collection underscore the need for continued innovation. We also explicate the causal factors behind recent benchmark performances, distinguishing between gains derived from architectural scaling versus those stemming from specific optimization objectives. We further discuss emerging directions, including hybrid RL algorithms, verifier-guided training, and multi-objective alignment frameworks. This survey serves as a roadmap for researchers advancing RL-driven LLM development, balancing capability enhancement with safety and scalability.

Saksham Sahai Srivastava, Vaneet Aggarwal

University of Georgia, Athens, GA, USA · Purdue University, West Lafayette, IN, USA

Large Language Model Reinforcement Learning Offline Reinforcement Learning

Jun 20, 2025cs.LG

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning

A major bottleneck in scientific discovery consists of narrowing an exponentially large set of objects, such as proteins or molecules, to a small set of promising candidates with desirable properties. While this process can rely on expert knowledge, recent methods leverage reinforcement learning (RL) guided by a proxy reward function to enable this filtering. By employing various forms of entropy regularization, these methods aim to learn samplers that generate diverse candidates that are highly rated by the proxy function. In this work, we make two main contributions. First, we show that these methods are liable to generate overly diverse, suboptimal candidates in large search spaces. To address this issue, we introduce a novel unified operator that combines several regularized RL operators into a general framework that better targets peakier sampling distributions. Secondly, we offer a novel, robust RL perspective of this filtering process. The regularization can be interpreted as robustness to a compositional form of uncertainty in the proxy function (i.e., the true evaluation of a candidate differs from the proxy's evaluation). Our analysis leads us to a novel, easy-to-use algorithm we name trajectory general mellowmax (TGM): we show it identifies higher quality, diverse candidates than baselines in both synthetic and real-world tasks. Code: https://github.com/marcojira/tgm.

Marco Jiralerspong, Esther Derman, Danilo Vucetic +5

1Université de Montréal · 2Mila · 5Independent +1

Kullback-Leibler Regularization Rejection Sampling Offline Reinforcement Learning Logical Connectives Candidate

Jun 17, 2025cs.LG

Adaptive Reinforcement Learning for Unobservable Random Delays

In standard reinforcement learning (RL) settings, the interaction between the agent and the environment is typically modeled as a Markov decision process (MDP), which assumes that the agent observes the system state instantaneously, selects an action without delay, and executes it immediately. In real-world dynamic environments, such as cyber-physical systems, this assumption often breaks down due to delays in the interaction between the agent and the system. These delays can vary stochastically over time and are typically unobservable when deciding on an action. Existing methods deal with this uncertainty conservatively by assuming a known fixed upper bound on the delay, even if the delay is often much lower. In this work, we introduce the interaction layer, a general framework that enables agents to adaptively handle unobservable and time-varying delays. Specifically, the agent generates a matrix of possible future actions, anticipating a horizon of potential delays, to handle both unpredictable delays and lost action packets sent over networks. Building on this framework, we develop a model-based algorithm, Actor-Critic with Delay Adaptation (ACDA), which dynamically adjusts to delay patterns. Our method significantly outperforms state-of-the-art approaches across a wide range of locomotion benchmark environments, including real-world measured delays.

John Wikman, Alexandre Proutiere, David Broman

EECS and Digital Futures, KTH Royal Institute of Technology, Stockholm, Sweden.

Offline Reinforcement Learning Mujoco Cyber-Physical System Action Expert

Jun 9, 2025cs.LG

ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequence-structure datasets and by misalignment between supervised objectives and real design goals. We present ProteinZero, an online reinforcement learning framework for inverse folding models that enables scalable, automated, and continuous self-improvement with computationally efficient feedback. ProteinZero employs a reward pipeline that combines structural guidance from ESMFold with a novel self-derived ddG predictor, providing stable multi-objective signals while avoiding the prohibitive cost of physics-based methods. To ensure robustness in online RL, we further introduce a novel embedding-level diversity regularizer that mitigates mode collapse and promotes sequence-level diversity among generated designs. Within a general RL formulation balancing multi-reward optimization, KL-divergence from a reference model, and diversity regularization, ProteinZero achieves robust improvements across designability, predicted stability, recovery, and diversity. On the CATH-4.3 benchmark, it consistently outperforms state-of-the-art baselines including ProteinMPNN, ESM-IF, and InstructPLM, reducing design failure rates by 36-48% and achieving success rates above 90% across diverse folds. Importantly, a complete RL run can be executed on a single 8xGPU node within three days, including reward computation and data generation. These results indicate that efficient online RL fine-tuning can complement supervised pretraining by allowing protein generative models to evolve continuously from their own outputs and optimize multiple design objectives without labeled data, opening new possibilities for exploring the vast protein design space. Code and model checkpoints are available at https://github.com/ziwenwang28/ProteinZero.

Ziwen Wang, Jiajun Fan, Ruihan Guo +3

Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, IL, USA · DOE Center for Advanced Bioenergy and Bioproducts Innovation, University of Illinois Urbana-Champaign, Urbana, IL, USA

Protein Design Protein Offline Reinforcement Learning Inverse Problem

Jun 2, 2025cs.LG

SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems

Most existing safe reinforcement learning (RL) benchmarks focus on robotics and control tasks, offering limited relevance to high-stakes domains that involve structured constraints, mixed-integer decisions, and industrial complexity. This gap hinders the advancement and deployment of safe RL in critical areas such as energy systems, manufacturing, and supply chains. To address this limitation, we present SafeOR-Gym, a benchmark suite of nine operations research (OR) environments tailored for safe RL under complex constraints. Each environment captures a realistic planning, scheduling, or control problems characterized by cost-based constraint violations, planning horizons, and hybrid discrete-continuous action spaces. The suite integrates seamlessly with the Constrained Markov Decision Process (CMDP) interface provided by OmniSafe. We evaluate several state-of-the-art safe RL algorithms across these environments, revealing a wide range of performance: while some tasks are tractable, others expose fundamental limitations in current approaches. SafeORGym provides a challenging and practical testbed that aims to catalyze future research in safe RL for real-world decision-making problems.

Asha Ramanujam, Adam Elyoumi, Hao Chen +5

Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN · Energy Sciences, ExxonMobil Technology and Engineering Company, Annandale, NJ · Energy Sciences, ExxonMobil Technology and Engineering Company, Annadale, NJ

Safety Constraints Operations Research Offline Reinforcement Learning Markov Decision Processes Skillgym Action Space

May 29, 2025cs.LG

Normalizing Flows are Capable Models for Continuous Control

Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price of accommodating these models into their algorithms -- diffusion models are expressive, but are computationally intensive due to their reliance on solving differential equations, while autoregressive transformer models are scalable but typically require learning discrete representations. Normalizing flows (NFs), by contrast, seem to provide an appealing alternative, as they enable likelihoods and sampling without solving differential equations or autoregressive architectures. However, their potential in RL has received limited attention, partly due to the prevailing belief that normalizing flows lack sufficient expressivity. We show that this is not the case. Building on recent work in NFs, we propose a single NF architecture which integrates seamlessly into RL algorithms, serving as a policy, Q-function, and occupancy measure. Our approach leads to much simpler algorithms, and achieves higher performance in imitation learning, offline, goal conditioned RL and unsupervised RL.

Raj Ghugare, Benjamin Eysenbach

Department of Computer Science Princeton University

Normalizing Flows Offline Reinforcement Learning Autoregressive Transformers Imitation Learning

May 28, 2025cs.LG

Fully Offline Reinforcement Learning

Offline RL (ORL) promises safe and sample-efficient deployment but existing methods rely on undocumented online interactions for hyperparameter tuning and lack reliable fully offline estimates of initial online performance. We introduce SOReL, a fully offline Bayesian model-based RL method that learns a posterior over dynamics, estimates policy value via predictive uncertainty, and enables complete offline hyperparameter selection. We further propose TOReL, which extends this tuning framework to arbitrary model-free and model-based ORL algorithms. We provide a regret analysis showing that Bayesian offline RL achieves the minimax-optimal parametric rate under standard regularity conditions. Together, our methods establish a practical and theoretically grounded framework for fully offline RL.

Mattie Fellows, Clarisse Wibault, Uljad Berdica +3

Foerster Lab for AI Research (FLAIR), Department of Engineering Science, University of Oxford · Machine Learning Research Group, Department of Engineering Science, University of Oxford

Model-Based Reinforcement Learning Offline Reinforcement Learning Minimax Rate

May 26, 2025cs.LG

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or rewards. In this work, we question whether such a strong assumption is required to launch backdoor attacks against RL. To answer this question, we propose the \underline{S}upply-\underline{C}h\underline{a}in \underline{B}ackdoor (SCAB) attack, which targets a common RL workflow: training agents using external agents that are provided separately or embedded within the environment. In contrast to prior works, our attack only relies on legitimate interactions of the RL agent with the supplied agents. Despite this limited access model, by poisoning a mere

3\%

of training experiences, our attack can successfully activate over

90\%

of triggered actions, reducing the average episodic return by

80\%

for the victim. Our novel attack demonstrates that RL attacks are likely to become a reality under untrusted RL training supply-chains.

Shijie Liu, Andrew C. Cullen, Paul Montague +2

School of Computing and Information Systems, University of Melbourne, Parkville, Australia · DST Group, Adelaide

Offline Reinforcement Learning Kernel-Resident Tool Governance Gateway House

May 18, 2025cs.LG

Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment may differ from its training dynamics. However, most existing studies focus on model-based settings and provide only asymptotic guarantees, hindering their principled understanding and practical deployment, especially in data-limited scenarios. We aim to close this gap by proposing a model-free algorithm, \textbf{Robust Halpern Iteration (RHI)}. We first design our algorithm based on a black-box sampling oracle, which can estimate the worst-case performance accurately. We then derive the finite sample complexity of RHI under the generative model setting, assuming the sampling oracle. To concretely design such an oracle, we propose a

K

-order multi-level Monte-Carlo estimator, which is shown to have a lower bias compared to prior methods. We further instantiate our design for multiple uncertainty models, including KL and

χ^2

divergence sets, and show that our RHI algorithm achieves an

\varepsilon

-optimal robust policy with a sample complexity of

\tilde{\mathcal{O}}\left( \frac{SA\mathcal{H}^2}{\varepsilon^{(2+o(1))}}\right)

, where

S,A

are the number of states and actions, and

\mathcal{H}

is the robust optimal span. Our result asymptotically matches the best complexity in robust average reward RL.

Zachary Roch, George Atia, Yue Wang

Department of Electrical and Computer Engineering, University of Central Florida, Orlando, Florida, USA. · Department of Computer Science, University of Central Florida, Orlando, Florida, USA.

Model-Free Offline Reinforcement Learning Optimal Policies Sample Complexity Newton

Apr 23, 2025cs.RO

HERB: Human-augmented Efficient Reinforcement learning for Bin-packing

Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. When dealing with highly diverse 3D objects (household or grocery items), closed-form solutions are infeasible, and heuristic or model-free Reinforcement Learning~(RL) methods tend to focus solely on geometric optimization, relying on exhaustive searches of the discretized solution space. This leads to long training times (for pure RL) and high latency (heuristics), limited transferability to robotic scenarios, and ultimately ignores object characteristics (fragility, deformability) and human preferences. We propose HERB, a human-augmented RL framework for packing irregular objects, the first to explore the potential of learning from human demonstrations to solve this complex task. It leverages human demonstrations of packing strategies, which inherently exhibit latent factors such as space optimization, stability, and object properties that are difficult to model explicitly. The human-expert data is combined with RL exploration to provide the placement of each object inside the container. Experimental results show that our method outperforms heuristic, purely RL-based, and imitation learning approaches in packing efficiency and latency. Qualitative results highlight that our packing strategy produces more stable, human-like arrangements, which we expect to be more appropriate and widely accepted. Finally, we demonstrate the real-world feasibility of our method on a robotic system.

Gojko Perovic, Nuno Ferreira Duarte, Atabak Dehban +3

BioRobotics Institute, Scuola Superiore Sant’Anna, Pisa, Italy, and with the Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, Italy. · Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal.

Scalable Robot Learning Offline Reinforcement Learning Model-Free Reinforcement Learning Shape Optimization

Apr 12, 2025cs.LG

Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making

The primary goal of my Ph.D. study is to develop provably efficient and practical algorithms for data-driven sequential decision-making under uncertainty. My work focuses on reinforcement learning (RL), multi-armed bandits, and their applications, including recommendation systems, computer networks, video analytics, and large language models (LLMs). Sequential decision-making methods, such as bandits and RL, have demonstrated remarkable success - ranging from outperforming human players in complex games like Atari and Go to advancing robotics, recommendation systems, and fine-tuning LLMs. Despite these successes, many established algorithms rely on idealized models that can fail under model misspecifications or adversarial perturbations, particularly in settings where accurate prior knowledge of the underlying model class is unavailable or where malicious users operate within dynamic systems. These challenges are pervasive in real-world applications, where robust and adaptive solutions are critical. Furthermore, while worst-case guarantees provide theoretical reliability, they often fail to capture instance-dependent performance, which can lead to more efficient and practical solutions. Another key challenge lies in generalizing to new, unseen environments, a crucial requirement for deploying these methods in dynamic and unpredictable settings. To address these limitations, my research aims to develop more efficient, robust, instance-adaptive, and generalizable sequential decision-making algorithms for both reinforcement learning and bandits. Towards this end, I focus on developing more efficient, robust, instance-adaptive, and generalizable for both general reinforcement learning (RL) and bandits.

Zhiyong Wang

Department of Computer Science and Engineering, The Chinese University of Hong Kong

Sequential Decision Making Offline Reinforcement Learning

Mar 31, 2025cs.LG

A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective

Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD). Despite rapid advancements in RL and AD, a systematic description and interpretation of the RL design process tailored to diverse driving tasks remains underdeveloped. This survey provides a comprehensive review of RL-based MoP for AD, focusing on lessons from task-specific perspectives. We first outline the fundamentals of RL methodologies, and then survey their applications in MoP, analyzing scenario-specific features and task requirements to shed light on their influence on RL design choices. Building on this analysis, we summarize key design experiences, extract insights from various driving task applications, and provide guidance for future implementations. Additionally, we examine the frontier challenges in RL-based MoP, review recent efforts to addresse these challenges, and propose strategies for overcoming unresolved issues.

Zhuoren Li, Guizhe Jin, Ran Yu +8

College of Automotive and Energy Engineering, Tongji University, Shanghai 201804, China

Autonomous Driving Motion Planning Offline Reinforcement Learning Perspective

Mar 1, 2025cs.LG

Distributionally Robust Reinforcement Learning with Human Feedback

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream task differs significantly from the preference dataset used in fine-tuning. In order to mitigate this problem, we introduce a distributionally robust RLHF for fine-tuning LLMs. In particular, our goal is to ensure that a fine-tuned model retains its performance even when the distribution of prompts significantly differs from the distribution encountered during fine-tuning. We formulate distributionally robust optimization (DRO) version of two popular fine-tuning methods -- (1) reward-based RLHF and (2) reward-free DPO (direct preference optimization). We propose a minibatch gradient descent based algorithms for both of them, and theoretically prove convergence guarantees for the algorithms. Subsequently, we evaluate our algorithms on an out-of-distribution (OOD) task by first training the model on the Unified-Feedback dataset and evaluating its performance on two different datasets. The experimental results show that our robust training improves the accuracy of the learned reward models on average, and markedly on some tasks, such as reasoning. Furthermore, we show that the robust versions of policy optimization methods, similarly improve performance on OOD tasks.

Debmalya Mandal, Paulius Sasnauskas, Goran Radanovic

Dept. of Computer Science University of Warwick, UK · Department of Computing Science University of Alberta, Edmonton, Canada · Max-Planck Institute for Software Systems, Germany

Reinforcement Learning From Human Feedback Distributional Reinforcement Learning Offline Reinforcement Learning

Feb 6, 2025cs.CL

Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents

The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive frameworks for dynamically changing environments. This paper introduces \texttt{RL-Focal}, a two-stage RL agent framework that routes and ensembles LLMs. \textit{First}, we develop the Decider RL-agent, which learns to dynamically select an ensemble of small size (

m_i

) among

N

LLMs (

m_i \ll N

) for incoming queries from a user-defined downstream task

i

, by maximizing both error-diversity and reasoning-performance of the selected ensemble through iterative updates of task-adaptive rewards and policy. \textit{Second}, to enable effective fusion of dynamically selected LLMs, we develop the stage-2 Fusion RL-agent, which learns to resolve reasoning conflicts from different LLMs and dynamically adapt to different ensemble teams composed by the Decider Agent for different downstream tasks. {\em Third}, we introduce the focal diversity metric to better model the error correlations among multiple LLMs further improving the generalization performance of the Decider Agent, which actively prunes the ensemble combinations. By focal diversity, we enhance performance across tasks by effectively promoting reward-aware and policy-adaptive ensemble selection and inference fusion. Extensive evaluations on five benchmarks show that RL-Focal achieves the performance improvement of 8.48% with an ensemble of small size compared to the best individual LLM in a pool and offers stronger robustness. Code is available here.

Selim Furkan Tekin, Gaowen Liu, Ramana Rao Kompella +1

Georgia Institute of Technology · Cisco Systems

Large Language Model Reinforcement Learning Ensemble Offline Reinforcement Learning

Oct 31, 2024cs.AI

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner

The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is often scarce. The self-taught reasoner (STaR) framework addresses this by using reinforcement learning to automatically generate reasoning steps, reducing reliance on human-labeled data. Although STaR and its variants have demonstrated empirical success, a theoretical foundation explaining these improvements is lacking. This work provides a theoretical framework for understanding the effectiveness of reinforcement learning on CoT reasoning and STaR. Our contributions are: (1) criteria for the quality of pre-trained models necessary to initiate effective reasoning improvement; (2) an analysis of policy improvement, showing why LLM reasoning improves iteratively with STaR; (3) conditions for convergence to an optimal reasoning policy; and (4) an examination of STaR's robustness, explaining how it can improve reasoning even when incorporating occasional incorrect steps. We also run RL-STaR on GPT-2, Qwen2.5-0.5B and Phi-3-mini, and the measured return curves follow the ones the analysis predicts. This framework bridges empirical findings with theoretical insights, advancing reinforcement learning approaches for reasoning in LLMs.

Fu-Chieh Chang, Yu-Ting Lee, Hui-Ying Shih +2

MediaTek Research, Taipei, Taiwan · Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan · Department of Mathematical Sciences, National Chengchi University, Taipei, Taiwan +2

Large Language Model Reinforcement Learning LLM Reasoning Strategies Offline Reinforcement Learning Unsupervised On-Policy Self-Distillation Theory

Oct 18, 2024cs.LG

Streaming Deep Reinforcement Learning Finally Works

Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streaming learning has remained a persistent challenge in modern deep reinforcement learning (RL). Instead, most deep RL algorithms learn from old experience by storing past interactions in a buffer. We show that both classical streaming RL, such as Q-learning and actor-critic, when used with deep neural networks, and batch deep RL, such as PPO, SAC, and DQN, when adapted to the streaming setting, often fail to learn. Across 58 Atari games and 50 continuous-control tasks, we find that these methods, in aggregate, perform close to random policies despite extensive task-specific hyperparameter searches. We call this pattern stream barrier. Here, we introduce Stream-X, a shared recipe for streaming deep RL algorithms that combines signal normalization, representation stabilization, and controlled parameter updates. By applying Stream-X to several base streaming RL algorithms, we provide the first family of deep RL algorithms to overcome the stream barrier. Using one prescribed hyperparameter configuration per algorithm across tasks, Stream-X substantially improves aggregate performance, often on par with batch RL algorithms. Beyond these benchmarks, we demonstrate learning with Stream-X algorithms under nonstationarity and resource constraints. Stream-AC, one of the Stream-X algorithms, repeatedly recovers performance across alternating floor-friction regimes in simulation, outperforming the evaluated PPO and SAC baselines. It also learns a heading tracking task on a robot using proprioceptive and visual features from the on-board camera in a naturally changing laboratory environment. Stream-Q learns a Pong game from pixels directly on an ESP32-S3 microcontroller, a device with limited compute and memory.

Mohamed Elsayed, Elena Sorina Lupu, Gautham Vasan +1

Department of Computing Science, University of Alberta, Edmonton, Canada · Alberta Machine Intelligence Institute (Amii) · Canada CIFAR AI Chair

Offline Reinforcement Learning Q-Learning

Aug 26, 2024cs.RO

A Survey on Reinforcement Learning Applications in SLAM

Simultaneous localization and mapping (SLAM) allows a mobile robot or autonomous vehicle to build a map of an unknown environment while estimating its own pose within that map. Reinforcement learning (RL), in which an agent learns a decision policy from interaction and reward, has been applied to decide how such systems move, explore, and recognize places they have visited before. This survey reviews the applications of RL in SLAM. We first distinguish passive SLAM, in which the robot's motion is not chosen by the SLAM system, from active SLAM, in which it is, and summarize the sensors that provide the input to SLAM. We then introduce the RL methods used in this literature, from value-based and policy-based methods to actor-critic and deep RL. Next, we classify RL applications in SLAM into three categories: path planning, including environment exploration and obstacle avoidance; loop closure detection; and active SLAM. Thirteen representative studies are compared in terms of their simulation environment, deep learning method, SLAM method, and RL algorithm. Most of these studies are evaluated mainly in simulation, and value-based methods from the deep Q-network family are the most common. Finally, we discuss the challenges of applying RL to SLAM, namely computational demands, safety, generalization, high-dimensional state and action spaces, sample efficiency, and sensor and actuator delays, and we outline directions for future research.

Mohammad Dehghani Tezerjani, Mohammad Khoshnazar, Mohammadhamed Tangestanizadeh +2

Computer Science and Engineering, University of North Texas, Denton, USA · Institute of Artificial Intelligence, University of Bremen, Bremen, Germany · Computer Science and Engineering, University of California Santa Cruz, Santa Cruz, USA +1

Simultaneous Localization And Mapping Robot Navigation Offline Reinforcement Learning Obstacle Avoidance Survey

Jul 31, 2024cs.LG

ProSpec RL: Plan Ahead, then Execute

Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstream model-free Reinforcement Learning (RL) methods lack the ability to proactively envision future scenarios, plan, and guide strategies. These methods typically rely on trial and error to adjust policy functions, aiming to maximize cumulative rewards or long-term value, even if such high-reward decisions place the environment in extremely dangerous states. To address this, we propose the Prospective (ProSpec) RL method, which makes higher-value, lower-risk optimal decisions by imagining future n-stream trajectories. Specifically, ProSpec employs a dynamic model to predict future states (termed "imagined states") based on the current state and a series of sampled actions. Furthermore, we integrate the concept of Model Predictive Control and introduce a cycle consistency constraint that allows the agent to evaluate and select the optimal actions from these trajectories. Moreover, ProSpec employs cycle consistency to mitigate two fundamental issues in RL: augmenting state reversibility to avoid irreversible events (low risk) and augmenting actions to generate numerous virtual trajectories, thereby improving data efficiency. We validated the effectiveness of our method on the DMControl benchmarks, where our approach achieved significant performance improvements. Code will be open-sourced upon acceptance.

Liangliang Liu, Yi Guan, BoRan Wang +5

1The Faculty of Computing, Harbin Institute of Technology, Harbin, China · 2The Artificial Intelligence Institute, Harbin Institute of Technology, ShenZhen, China · 3The Artificial Intelligence Institute, Harbin Institute of Technology, Harbin, China

Model-Free Reinforcement Learning Offline Reinforcement Learning

Jul 12, 2024cs.RO

Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP

Object-oriented embodied navigation tasks require agents to locate specific objects, either defined by category or images, in unseen environments. While recent methods have made progress in extending closed-set models to open-vocabulary scenarios with foundation models, they typically rely on training-free large language models (LLMs) or finetuning with end-to-end reinforcement learning (RL). However, they face challenges in efficiency (e.g., the overhead and cost of LLM inference) and limited generalization from intensive RL training. In this paper, we propose OVExp, a training-efficient framework for open-vocabulary exploration. We make the first effort to demonstrate the generalization capabilities of semantic map-based goal prediction networks using Dense CLIP models. A major challenge is that preserving both precise point-wise object locations and generalizable visual representations in the semantic map leads to unaffordable training costs. To address this, we design a Cross-Modal Transfer on Semantic Mapping strategy which adapts an intriguing text-only training and transfer to multi-model semantic mapping and goals in test-time. Despite relying on text-based spatial layouts with limited objects, OVExp demonstrates robust generalization to unseentargets on established ObjectNav benchmarks.

Meng Wei, Chenyang Wan, Tai Wang +6

Shanghai AI Lab · Zhejiang University · The University of Hong Kong

Vision-Language Navigation Open-Vocabulary Semantic Mapping Contrastive Language-Image Pre-Training Model Visual Representations Offline Reinforcement Learning

Jun 12, 2024stat.ML

Decision-Centered Abstractions via Orthogonal Estimation of Difference-of-Q Functions

Offline reinforcement learning enables evaluation and optimization of sequential decisions from historical data, when it is not possible to deploy new policies online due to safety, cost, and other concerns. Big data advances enable rich state information, but may naively include reward- and action- irrelevant dynamics that are ultimately unnecessary for learning optimal actions. We introduce state abstractions that target preservation of the difference-of-Q functions, and we propose to learn these abstractions via causal machine learning of the difference-of-Q function and standard statistical sparse learning. Under a nonparametric additive-rewards model, we characterize when decision-centered abstractions are simpler than the full state space, motivating our estimation procedure. We develop a dynamic generalization of the R learner (Nie et al. 2021, Lewis and Syrgkanis 2021) for estimating difference of Q-functions, for discrete-valued actions a, a0. We leverage orthogonal estimation to improve convergence rates, even if the required estimates of Q and behavior policy converge at slower rates and prove consistency of policy optimization under a margin condition. The method can leverage black-box estimators of the Q-function and behavior policy to target estimation of a more structured Q-function contrast, and uses simple squared-loss minimization. We demonstrate variance improvements from our estimator and how our approach enables us to isolate the information needed for sequential decision-making, which can be less than that for state prediction, in simulated data and simulator-augmented real data.

Defu Cao, Angela Zhou

University of Southern California

Offline Reinforcement Learning Reward Functions

Apr 22, 2024cs.LG

Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty

Uncertainties in transition dynamics pose a critical challenge in reinforcement learning (RL), often resulting in performance degradation of trained policies when deployed on hardware. Many robust RL approaches follow two strategies: enforcing smoothness in actor or actor-critic modules with Lipschitz regularization, or learning robust Bellman operators. However, the first strategy does not investigate the impact of critic-only Lipschitz regularization on policy robustness, while the second lacks comprehensive validation in real-world scenarios. Building on this gap and prior work, we propose PPO-PGDLC, an algorithm based on Proximal Policy Optimization (PPO) that integrates Projected Gradient Descent (PGD) with a Lipschitz-regularized critic (LC). The PGD component calculates the adversarial state within an uncertainty set to approximate the robust Bellman operator, and the Lipschitz-regularized critic further improves the smoothness of learned policies. Experimental results on two classic control tasks and one real-world robotic locomotion task demonstrate that, compared to several baseline algorithms, PPO-PGDLC achieves better performance and predicts smoother actions under environmental perturbations.

Xulin Chen, Ruipeng Liu, Zhenyu Gan +1

College of Engineering & Computer Science, Syracuse University

Proximal Policy Optimization Offline Reinforcement Learning Lipschitz Continuity Transitions Smoothing Uncertainty+1

Apr 4, 2024cs.LG

Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms

The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to addressing this challenge is distributionally robust RL, often framed as a robust Markov decision process (RMDP). In this framework, the objective is to find a robust policy that achieves good performance under the worst-case scenario among all environments within a pre-specified uncertainty set centered around the training environment. Unlike previous work, which relies on a generative model or a pre-collected offline dataset enjoying good coverage of the deployment environment, we tackle robust RL via interactive data collection, where the learner interacts with the training environment only and refines the policy through trial and error. In this robust RL paradigm, two main challenges emerge: managing distributional robustness while striking a balance between exploration and exploitation during data collection. Initially, we establish that sample-efficient learning without additional assumptions is unattainable owing to the curse of support shift; i.e., the potential disjointedness of the distributional supports between the training and testing environments. To circumvent such a hardness result, we introduce the vanishing minimal value assumption to RMDPs with a total-variation (TV) distance robust set, postulating that the minimal value of the optimal robust value function is zero. We prove that such an assumption effectively eliminates support shift pathologies for RMDPs with a TV distance robust set, and present an algorithm with near-optimal sample complexity. To demonstrate the breadth of our framework, we extend our algorithm and theory to new robust set formulations and robust Markov games. To illustrate the operational relevance, we apply our algorithm to data-driven robust inventory control.

Miao Lu, Han Zhong, Tong Zhang +1

†Department of Management Science and Engineering, Stanford University. · ‡Center for Data Science, Peking University. · §Department of Computer Science, University of Illinois Urbana-Champaign.

Distributional Reinforcement Learning Offline Reinforcement Learning Markov Decision Processes Sim-To-Real Gap Optimal Hard

Aug 18, 2023cs.RO

Fading Expert Guidance: Bridging Model-Based and Learning-Based Control for Abortable Autonomous Overtaking

Overtaking on two-lane roads is a safety-critical decision-making problem for autonomous vehicles, since oncoming traffic may force the ego vehicle to abort and merge back to its original lane. Deep reinforcement learning (DRL) is promising for such continuous-control tasks, but it requires substantial interaction data and may produce unsafe exploratory actions during training. Model-based controllers provide structured behavior, but depend on model fidelity and hand-designed logic. This paper proposes a fading expert-guidance framework that uses a model-based controller to guide DRL training for autonomous overtaking. The expert combines a constrained iterative LQR (CiLQR) planner with PID-based auxiliary controllers, activated when the optimized plan becomes infeasible. The expert action enters the actor objective through a fading term, interpreted as a time-varying soft trust region around the expert policy. This term first biases the policy toward the expert and then vanishes, allowing optimization according to the reinforcement-learning objective. The method is evaluated with PPO, TD3, and SAC. Simulations with bidirectional traffic show improved sample efficiency and final task performance. The safety effects are algorithm-dependent: guidance reduces vehicle collisions for SAC, eliminates boundary collisions for TD3, and leaves the PPO collision profile unchanged. Overall, the results support fading expert guidance as a practical mechanism for transferring model-based driving knowledge to learning-based controllers without restricting the final policy to imitation in an abortable overtaking task with bidirectional traffic.

Jinxiong Lu, Gokhan Alcan, Ville Kyrki

Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, 02150 Espoo, Finland

Reinforcement Learning Control Robust Trajectory Offline Reinforcement Learning Bridging Language

Jul 29, 2023cs.LG

Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip

Reinforcement learning (RL) performs well in continuous-control tasks, but evolving hidden disturbances create partial observability: the agent must infer decision-relevant latent dynamics from interaction history. This study investigates how observation history, action history, history length, and network structure affect recurrent Twin Delayed Deep Deterministic Policy Gradient (TD3) agents. Three recurrent architectures are evaluated under controlled disturbances with different temporal characteristics. Results show that action history is particularly important when observed responses depend on previous actions, and that processing past and current action-observation information within a unified temporal sequence improves performance compared with using separate branches. We also introduce H-TD3, which reuses recurrent states generated by the actor to initialize the critic, reducing duplicated sequence processing. The architectures are further tested in a simulation-based differential-drive rover motion-regulation task under hidden asymmetric wheel slip. Recurrent architectures retain their advantage under the physically motivated multiplicative wheel-slip model, while policies trained with abstract temporally structured disturbances transfer more effectively to previously unseen wheel-slip dynamics than policies trained without disturbances. These findings provide practical guidance for recurrent RL under partial observability and evolving hidden disturbances.

Saki Omi, Hyo-Sang Shin, Namhoon Cho +2

Space Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg · School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield, U.K. · Department of Aerospace Engineering, Seoul National University, Seoul, South Korea

Offline Reinforcement Learning Wheel Recurrent State Latent Dynamics

Jun 23, 2023cs.AI

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams

We study a class of reinforcement learning (RL) tasks where the objective of the agent is to accomplish temporally extended goals. In this setting, a common approach is to represent the tasks as deterministic finite automata (DFA) and integrate them into the state-space for RL algorithms. However, while these machines model the reward function, they often overlook the causal knowledge about the environment. To address this limitation, we propose the Temporal-Logic-based Causal Diagram (TL-CD) in RL, which captures the temporal causal relationships between different properties of the environment. We exploit the TL-CD to devise an RL algorithm in which an agent requires significantly less exploration of the environment. To this end, based on a TL-CD and a task DFA, we identify configurations where the agent can determine the expected rewards early during an exploration. Through a series of case studies, we demonstrate the benefits of using TL-CDs, particularly the faster convergence of the algorithm to an optimal policy due to reduced exploration of the environment.

Yash Paliwal, Rajarshi Roy, Jean-Raphaël Gaglione +5

Arizona State University, Arizona, USA · Max Planck Institute for Software Systems, Kaiserslautern, Germany · University of Texas at Austin, Texas, USA +3

Offline Reinforcement Learning Linear Temporal Logics Automata State Space

Date pendingcs.AI

Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning

Developing agents capable of exploring, planning and learning in complex open-ended environments is a grand challenge in artificial intelligence (AI). Hierarchical reinforcement learning (HRL) offers a promising solution to this challenge by discovering and exploiting the temporal structure within a stream of experience. The strong appeal of the HRL framework has led to a rich and diverse body of literature attempting to discover a useful structure. However, it is still not clear how one might define what constitutes good structure in the first place, or the kind of problems in which identifying it may be helpful. This work aims to identify the benefits of HRL from the perspective of the fundamental challenges in decision-making, as well as highlight its impact on the performance trade-offs of AI agents. Through these benefits, we then cover the families of methods that discover temporal structure in HRL, ranging from learning directly from online experience to offline datasets, to leveraging large language models (LLMs). Finally, we highlight the challenges of temporal structure discovery and the domains that are particularly well-suited for such endeavours.

Martin Klissarov, Akhil Bagaria, Ziyan Luo +3

Mila, McGill University · Amazon · Amii, University of Alberta Canada CIFAR AI Chair

Hierarchical Reinforcement Learning Offline Reinforcement Learning Hierarchical

Date pendingcs.LG

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-collocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL frameworks face challenges in managing complex dataflows and resolving resource idling. Furthermore, most existing frameworks are tightly coupled with LLM training or inference engines, making them difficult to support custom-designed engines. To address these challenges, we propose AsyncFlow, an asynchronous streaming RL framework tailored for efficient post-training. Specifically, we introduce a distributed data storage and transfer module that provides panoramic data management and fine-grained scheduling capabilities in a fully streamed manner. This architecture inherently enables automated pipeline overlapping among RL tasks and dynamic load-balancing. Moreover, we propose an asynchronous producer-consumer workflow, which is engineered to minimize computational idleness by strategically deferring the parameter update process within staleness thresholds. Finally, the core capabilities of AsyncFlow are architecturally decoupled from underlying training and inference engines and encapsulated by service-oriented user interfaces, offering a modular and customizable user experience. Extensive experiments demonstrate an average throughput of 1.59x compared to the state-of-the-art baseline. The architecture presented in this work provides actionable insights for designing next-generation RL training systems.

Zhenyu Han, Ansheng You, Haibo Wang +16

Huawei · Individual Researcher

Asynchronous Execution Efficient Large Language Model Post-Training Offline Reinforcement Learning

Date pendingcs.RO

CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots

For effective deployment in real-world environments, humanoid robots must autonomously navigate a diverse range of complex terrains with abrupt transitions. While the Vanilla mixture of experts (MoE) framework is theoretically capable of modeling diverse terrain features, in practice, the gating network exhibits nearly uniform expert activations across different terrains, weakening the expert specialization and limiting the model's expressive power. To address this limitation, we introduce CMoE, a novel single-stage reinforcement learning framework that integrates contrastive learning to refine expert activation distributions. By imposing contrastive constraints, CMoE maximizes the consistency of expert activations within the same terrain while minimizing their similarity across different terrains, thereby encouraging experts to specialize in distinct terrain types. We validated our approach on the Unitree G1 humanoid robot through a series of challenging experiments. Results demonstrate that CMoE enables the robot to traverse continuous steps up to 20 cm high and gaps up to 80 cm wide, while achieving robust and natural gait across diverse mixed terrains, surpassing the limits of existing methods. To support further research and foster community development, we release our code publicly.

Shihao Ma, Hongjin Chen, Zijun Xu +6

College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China, 200433

Full-Body Humanoid Control Terrain Motion Control Offline Reinforcement Learning Experts Contrastive Learning

Date pendingcs.LG

UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors

This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data. Existing approaches often require large-scale player trajectories, train separate models for different player types, or provide no direct mapping between interpretable behavioral parameters and the learned policy, limiting their scalability and controllability. We define player behavior in an N-dimensional continuous space and uniformly sample target behavior vectors from a region that encompasses the subset representing real human styles. During training, each agent receives both its current and target behavior vectors as input, and the reward is based on the normalized reduction in distance between them. This allows the policy to learn how actions influence behavioral statistics, enabling smooth control over attributes such as aggressiveness, mobility, and cooperativeness. A single PPO-based multi-agent policy can reproduce new or unseen play styles without retraining. Experiments conducted in a custom multi-player Unity game show that the proposed framework produces significantly greater behavioral diversity than a win-only baseline and reliably matches specified behavior vectors across diverse targets. The method offers a scalable solution for automated playtesting, game balancing, human-like behavior simulation, and replacing disconnected players in online games.

Atahan Cilan, Atay Özgövde

Turkish Aerospace, Istanbul, Turkey · Department of Computer Engineering, Boğaziçi University, Istanbul, Turkey

Behavior Cloning Offline Reinforcement Learning

Date pendingcs.LG

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while cascade RL is cumbersome and prone to catastrophic forgetting. We propose DiffusionOPD, a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD). DiffusionOPD first trains task-specific teachers independently, then distills their capabilities into a unified student along the student own rollout trajectories. This decouples single-task exploration from multi-task integration and avoids the optimization burden of solving all tasks jointly from scratch. Theoretically, we lift the OPD framework from discrete tokens to continuous-state Markov processes, deriving a closed-form per-step KL objective that unifies both stochastic SDE and deterministic ODE refinement via mean-matching. We formally and empirically demonstrate that this analytic gradient provides lower variance and better generality compared to conventional PPO-style policy gradients. Extensive experiments show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance, while achieving state-of-the-art results on all evaluated benchmarks.

Quanhao Li, Junqiu Yu, Kaixun Jiang +7

Fudan University, China · Alibaba Group, China

Diffusion-Based Reinforcement Learning Methods Online-Policy Distillation Diffusion Models Multi--Task Learning Offline Reinforcement Learning Perspective

Date pendingcs.AI

CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution

Skill libraries improve the sample efficiency of agentic reinforcement learning (RL) by enabling large language model (LLM) agents to reuse procedural knowledge. Yet existing paradigms exhibit structural shortcomings: they either decouple skill evolution from policy optimization or instantiate meta-skills as fixed workflows. Both treat skills as passive objects to be managed, limiting the flexible evolution of skills and their co-adaptation with the reasoning agent. To address the limitations, we propose CoSkill, a unified multi-agent RL framework that recasts the static meta-skill workflow as a learnable Meta-Skill Agent and jointly trains it with a Reasoning Agent over a hierarchical skill library. By modeling the Reasoning and Meta-Skill Agents as a cooperative team sharing a single backbone, CoSkill enables end-to-end co-adaptation: the Reasoning Agent conditions its actions on a retrieved task skill and step skills selected from its child set, while its task performance guides the Meta-Skill Agent in refining those step skills. Experiments on ALFWorld and WebShop show that CoSkill substantially outperforms prior skill-based and RL baselines, achieving success rates of 98.4% and 90.6%, respectively (+3.5 and +6.2 pp). As shown in Figure 1, CoSkill achieves superior early-stage sample efficiency, asymptotic performance, and wall-clock efficiency. Our code is available at https://github.com/jinyuan-cookie/CoSkill.

Jinyuan Feng, Dongmin Li, Yiqun Chen +4

Institute of Automation, Chinese Academy of Sciences · Renmin University of China · ByteDance

Self-Evolving Skill Libraries Reusable Agent Skills Skill Evolution Agentic Reinforcement Learning Multi-Agent Reinforcement Learning Offline Reinforcement Learning

Date pendingcs.LG

Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning

Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity. Existing remedies such as entropy regularization or diversity bonuses often require fragile trade-offs that sacrifice performance for stochasticity or rely on heuristic metrics that can misalign policy rankings. We argue that diversity is more naturally understood as the rational response to uncertainty in the reward. When the reward function is not perfectly known--as is the case with ambiguous preferences or imperfect reward models--committing to a single action can be sub-optimal. Building on this, we propose a fundamental reformulation of the RL objective by replacing the scalar reward with a distribution over reward functions, and applying a non-linear objective over sets of actions. The result is a framework in which calibrated behavioural diversity emerges naturally, remains controllable through the reward function distribution, and is obtained without sacrificing expected reward. Focusing on the contextual bandit setting as commonly used in large language model (LLM) post-training, we derive a principled gradient estimator for this objective and prove that our formulation naturally generalizes both vanilla policy gradient and more recently developed action-set approaches. We provide didactic experiments which complement our theoretical results, and our large-scale empirical results in LLM reasoning further demonstrate that this framework offers a robust and theoretically grounded alternative for complex RL tasks where the traditional formulation of the problem fails to induce the desired breadth of agent behaviour.

Anthony GX-Chen, Ankit Anand, Gheorghe Comanici +7

New York University · Google DeepMind

Reward Functions Offline Reinforcement Learning Uncertainty Preference Alignment Learning