Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Momentum

144 papers in the last four weeks, up 243% on the four weeks before. 1.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,138

May 1, 2026cs.LG

Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation

Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning signal on challenging problems where none of the sampled solutions passes all tests. A common remedy is to use the test-case pass rate as a surrogate reward. In this work, we study pass-rate rewards in critic-free RL for code generation (e.g., GRPO and RLOO) and report a consistent pattern across base models and algorithms: despite alleviating reward sparsity, pass-rate rewards do not reliably improve final performance over binary rewards in rigorous controlled experiments. To understand this discrepancy, we analyze reward density and the resulting gradient directions. We find that pass-rate rewards are denser, but the induced gradient updates do not consistently move probability mass toward full-pass solutions. This arises because test-case pass rate is a miscalibrated surrogate for progress toward full correctness, and partial-pass solutions within the same group can induce conflicting gradient directions that cancel out. Overall, our results suggest that, in critic-free RL, pass-rate rewards are insufficient to improve code generation and motivate reward designs that better align optimization with the goal of full correctness.

Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang +3

State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China · School of Artificial Intelligence, Nanjing University, Nanjing 210023, China

RL for Code Generation Reinforcement Learning Critic-Free RL Reinforcement Learning with Verifiable Rewards Reward Design for RL

May 1, 2026cs.LG

Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization

Inverse reinforcement learning (IRL) learns a reward function and a corresponding policy that best fit the demonstration data of an expert. However, in the current IRL setting, the learner is isolated from the expert and can only passively observe the expert demonstrations. This limits the applicability of IRL to interactive settings, where the learner actively interacts with the expert and needs to infer the expert's reward function from the interactions. To bridge the gap, this paper studies interactive IRL (IIRL) where a learner aims to learn the reward function of an expert and a policy to interact with the expert during its interactions with the expert. We formulate IIRL as a stochastic bi-level optimization problem where the lower level learns a reward function to explain the behaviors of the expert, and the upper level learns a policy to interact with the expert. We develop a double-loop algorithm, Bi-level Interactive Scenarios Inverse Reinforcement Learning (BISIRL), which solves the lower-level problem in the inner loop and the upper-level problem in the outer loop. We formally guarantee that BISIRL converges and validate our algorithm through extensive experiments.

Yue Mao, Shicheng Liu, Siyuan Xu +1

Department of Mechanical Engineering, Pennsylvania State University · Department of Electrical Engineering, Pennsylvania State University

Reinforcement Learning

May 1, 2026cs.LG

Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation

Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls to planning and statistical estimation oracles. While recent advances have explored offline oracle-efficient algorithms, their computational complexity typically scales with the cardinality of the state and action spaces, rendering them intractable for large-scale or continuous environments. In this paper, we address this fundamental limitation by studying offline oracle-efficient episodic RL through the lens of log-barrier and log-determinant regularization. Specifically, for tabular Markov Decision Processes (MDPs), we propose a novel algorithm that achieves the optimal

\tilde{O}(\sqrt{T})

regret bound while requiring only

O(H\log\log T)

calls to both the offline statistical estimation and planning oracles when

T

is known and

O(H\log T)

calls when

T

is unknown. Crucially, this oracle complexity is entirely independent of the size of the state and action spaces. This strict independence drastically reduces the planning oracle complexity, representing a substantial improvement over existing offline oracle-efficient algorithms (Qian et al., 2024). Furthermore, we demonstrate the versatility of our framework by generalizing the algorithm to linear MDPs featuring infinite state spaces and arbitrary action spaces. We prove that this generalized approach successfully attains meaningful sub-linear regret. Consequently, our work yields the first doubly oracle-efficient (i.e., efficient with respect to both statistical estimation and policy optimization) regret minimization algorithm capable of solving MDPs with infinite state and action spaces, significantly expanding the boundaries of computationally tractable RL.

Haichen Hu, Jian Qian, David Simchi-Levi

Laboratory for Information and Decision Systems · Department of AI and Data Science

Regret Minimization in RL Markov Decision Processes Reinforcement Learning Linear Markov Decision Processes Model-Based RL

May 1, 2026cs.LG

Interpretable experiential learning based on state history and global feedback

A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model represented by a transition graph between sets of states, with transitions attributed with utility and evidence count. This model is expected to be suitable for solving reinforcement learning problem in resource-constrained environments. The model was thoroughly evaluated on the OpenAI Gym Atari Breakout benchmark, demonstrating performance comparable to some known neural network-based solutions.

Anton Kolonin

1The Artificial Intelligence Research Center, Novosibirsk State University, Russia · 2Aigents, Russia.

Reinforcement Learning Game-Playing Agents Interpretability in RL Model-Based RL

May 1, 2026cs.LG

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative Sample Reinforcement (NSR) mitigate this issue by upweighting penalty from negative samples, they may suppress the semantic distributions shared between positive and negative responses. To boost reasoning ability without losing diversity, this paper proposes negative sample projection Residual Reinforcement Learning (ResRL) that decouples similar semantic distributions among positive and negative responses. We theoretically link Lazy Likelihood Displacement (LLD) to negative-positive head-gradient interference and derive a single-forward proxy that upper-bounds representation alignment to guide conservative advantage reweighting. ResRL then projects negative-token hidden representations onto an SVD-based low-rank positive subspace and uses projection residuals to modulate negative gradients, improving reasoning while preserving diversity and outperforming strong baselines on average across twelve benchmarks spanning Mathematics, Code, Agent Tasks, and Function Calling. Notably, ResRL surpasses NSR on mathematical reasoning by 9.4% in Avg@16 and 7.0% in Pass@128. Code is available at https://github.com/1229095296/ResRL.git.

Zihan Lin, Xiaohan Wang, Jie Cao +6

MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China · Meituan, Beijing, China · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China.

RL for Language Models Reinforcement Learning RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards

Apr 30, 2026cs.LG

Data Deletion Can Help in Adaptive RL

Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Markov Decision Process (cMDP) framework, where a family of environments is indexed by a low-dimensional context unknown at test time. The standard approach decomposes the problem: train a so-called "universal policy" which assumes knowledge of the true context, then pair it with a context estimator which approximates context using the observed trajectory. We identify a simple, counterintuitive trick that substantially improves the estimator: randomly delete a fraction of the training buffer after each round. This works because data is collected across multiple rounds using progressively better policies, and older trajectories come from a different distribution than what the estimator will face at deployment time; random deletion creates an implicit exponential decay on older data while preserving diversity without requiring any explicit identification of which samples are stale. This reduces robustness gap by 30% for MLPs and by 6% on average for recurrent networks. Strikingly, it allows a narrow MLP with 5x fewer parameters to outperform a wide MLP trained without deletion. To understand when and why deletion helps, we analyze regularized empirical risk minimization with a mismatch between the train distribution and the distribution at deployment; in this idealized setting, we prove that removing a single uniformly random training point decreases expected test loss in expectation under mild conditions. For ridge regression we make this quantitative: deletion helps when the regularization coefficient is moderate and the signal-to-noise ratio (SNR) is sufficiently low, and, crucially, this SNR threshold gives a direct measure of how large the distribution mismatch between training and deployment must be for deletion to be beneficial.

Param Budhraja, Aditya Gangrade, Alex Olshevsky +1

Department of Electrical and Computer Engineering, Boston University, Boston, MA 02215, USA · Faculty of Electrical and Computer Engineering, Systems Engineering, Boston University, Boston, MA 02215, USA

Non-Stationary RL Reinforcement Learning Distribution Shift Experience Replay Policy Learning

Apr 30, 2026cs.LG

Pessimism-Free Offline Learning in General-Sum Games via KL Regularization

Offline multi-agent reinforcement learning in general-sum settings is challenged by the distribution shift between logged datasets and target equilibrium policies. While standard methods rely on manual pessimistic penalties, we demonstrate that KL regularization suffices to stabilize learning and achieve equilibrium recovery. We propose General-sum Anchored Nash Equilibrium (GANE), which recovers regularized Nash equilibria at an accelerated statistical rate of

\widetilde{O}(1/n)

. For computational tractability, we develop General-sum Anchored Mirror Descent (GAMD), an iterative algorithm converging to a Coarse Correlated Equilibrium at the standard rate of

\widetilde{O}(1/\sqrt{n}+1/T)

. These results establish KL regularization as a standalone mechanism for pessimism-free offline learning that achieves equivalent or accelerated rates in multi-player general-sum games.

Claire Chen, Yuheng Zhang

The Division of Physics, Mathematics and Astronomy California Institute of Technology · Department of Computer Science University of Illinois Urbana-Champaign

Nash Equilibrium Reinforcement Learning KL-Regularized RL Game Theory Offline RL Multi-Agent Reinforcement Learning+2

Apr 30, 2026cs.LG

Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback

Reinforcement learning from human feedback (RLHF) is a central post-training tool for aligning large language models, but its training reward is only a learned proxy for true human utility. This creates a decision problem under objective misspecification: the policy is optimized against an estimated reward, while deployment performance is governed by an unobserved population preference. The resulting gap leads to reward over-optimization, where proxy reward keeps improving after true quality deteriorates. We propose distributionally robust regret optimization (DRRO) for RLHF with a Wasserstein ambiguity set over reward laws, using promptwise

\ell_p

distances between reward vectors as transport costs. Unlike standard distributionally robust optimization, which pessimizes worst-case value, DRRO pessimizes worst-case regret relative to the best policy under the same plausible reward perturbation. We show that the expressive-policy problem decomposes into promptwise regret problems. For each prompt, the inner adversary has a dual-norm closed form; under the

\ell_1

transport cost used by our algorithm, the optimizer has a water-filling structure. These results lead to a practical policy-gradient algorithm that adds a simple sampled bonus to GRPO-style training. Theory and experiments both show that DRRO is less over-pessimistic than standard DRO and mitigates over-optimization more effectively than existing baselines.

Yikai Wang, Shang Liu, Jose Blanchet

Department of Statistics and Operations Research, University of North Carolina · Imperial Business School, Imperial College London · Department of Management Science and Engineering, Stanford University

Regret Minimization in RL Reinforcement Learning Distributionally Robust Optimization Wasserstein Distributionally Robust Optimization Distributionally Robust RL Robust RL+1

Apr 30, 2026cs.AI

RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses

Large language models (LLMs) make reward design in reinforcement learning substantially more scalable, but generated rewards are not automatically reliable training objectives. Existing work has focused primarily on generating, evolving, or selecting reward candidates, while paying less attention to when such candidates can be verified and deployed during policy optimization. We study this deployment-time problem by treating generated rewards as reward hypotheses whose utility depends on the competence of the current policy and the phase of training. We propose \textsc{RHyVE}, a competence-aware verification and phase-aware deployment protocol that compares small sets of reward hypotheses from shared policy checkpoints using short-horizon fork verification. Our experiments show that reward rankings are unreliable at low competence but become informative after task-dependent thresholds. On a sparse manipulation task, phase-aware deployment improves peak and retained performance under a locked protocol. Updated LLM-generated reward-candidate experiments show candidate-family-dependent behavior: generated pools can exhibit phase-dependent winner changes, but no fixed warm-up schedule is universally optimal. Held-out schedule selection, conservative selector baselines, compute-matched controls, and scale controls further show that \textsc{RHyVE} is best understood as a verification-informed deployment protocol rather than a universal scheduler. Dense and all-failure boundary experiments delimit the scope of the method. Together, these results suggest that reward generation and reward deployment should be studied as coupled problems: generated rewards must be verified and deployed under changing policy competence.

Feiyu Wu, Xu Zheng, Zhuocheng Wang +2

School of Cyber Engineering, Xidian University

Reinforcement Learning LLM-Guided RL Robotic RL Reward Design for RL

Apr 30, 2026cs.LG

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods mainly focus on supervised learning, and reinforcement learning in latent space remains highly unstable. We study this problem through the lens of Group Relative Policy Optimization (GRPO), and show that directly adapting GRPO to latent reasoning is fundamentally non-trivial: latent reasoning changes both the probability density and the sampling mechanism, causing three coupled bottlenecks: absence of intrinsic latent manifolds, where unconstrained exploration pushes rollouts off the valid latent manifold; exploration-optimization misalignment, where trajectory-level rewards can induce incorrect token-level updates; and latent mixture non-closure, where jointly reinforcing multiple correct latent paths can produce an invalid averaged state. To address them, we propose \textbf{Latent-GRPO}, which combines invalid-sample advantage masking, one-sided noise sampling, and optimal correct-path first-token selection. Across four low-difficulty benchmarks (e.g., GSM8K-Aug) and four high-difficulty benchmarks (e.g., AIME), Latent-GRPO improves over its latent initialization by 7.86 Pass@1 points on low-difficulty tasks and surpasses explicit GRPO by 4.27 points on high-difficulty tasks while using 3--4

\times

shorter reasoning chains. It also achieves stronger pass@

k

performance under Gumbel sampling. These results establish Latent-GRPO as an effective approach for stable and efficient latent reasoning.

Jingcheng Deng, Zihao Wei, Liang Pang +4

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences

Reinforcement Learning RL for Language Model Reasoning Group Relative Policy Optimization Continuous Latent Reasoning Latent Reasoning

Apr 30, 2026cs.AI

GUI Agents with Reinforcement Learning: Toward Digital Inhabitants

Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces visually. Yet supervised fine-tuning alone cannot handle long-horizon credit assignment, distribution shifts, and safe exploration in irreversible environments, making Reinforcement Learning (RL) a central methodology for advancing automation. In this work, we present the first comprehensive overview of the intersection between RL and GUI agents, and examine how this research direction may evolve toward digital inhabitants. We propose a principled taxonomy that organizes existing methods into Offline RL, Online RL, and Hybrid Strategies, and complement it with analyses of reward engineering, data efficiency, and key technical innovations. Our analysis reveals several emerging trends: the tension between reliability and scalability is motivating the adoption of composite, multi-tier reward architectures; GUI I/O latency bottlenecks are accelerating the shift toward world-model-based training, which can yield substantial performance gains; and the spontaneous emergence of System-2-style deliberation suggests that explicit reasoning supervision may not be necessary when sufficiently rich reward signals are available. We distill these findings into a roadmap covering process rewards, continual RL, cognitive architectures, and safe deployment, aiming to guide the next generation of robust GUI automation and its agent-native infrastructure.

Junan Hu, Jian Liu, Jingxiang Lai +6

1Shandong University · 2The Hong Kong University of Science and Technology · 3The Hong Kong University +2

Reinforcement Learning RL for GUI Agents GUI Agents Offline RL

Apr 30, 2026cs.CV

Leveraging Verifier-Based Reinforcement Learning in Image Editing

While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model for all editing tasks. Existing edit reward models usually give overall scores without detailed checks, ignoring different instruction requirements and causing biased rewards. To address this, we argue that the key is to move from a simple scorer to a reasoning verifier. We introduce Edit-R1, a framework that builds a chain-of-thought (CoT) verifier-based reasoning reward model (RRM) and then leverages it for downstream image editing. The Edit-RRM breaks instructions into distinct principles, evaluates the edited image against each principle, and aggregates these checks into an interpretable, fine-grained reward. To build such an RRM, we first apply supervised fine-tuning (SFT) as a ``cold-start'' to generate CoT reward trajectories. Then, we introduce Group Contrastive Preference Optimization (GCPO), a reinforcement learning algorithm that leverages human pairwise preference data to reinforce our pointwise RRM. After building the RRM, we use GRPO to train editing models with this non-differentiable yet powerful reward model. Extensive experiments demonstrate that our Edit-RRM surpasses powerful VLMs such as Seed-1.5-VL and Seed-1.6-VL as an editing-specific reward model, and we observe a clear scaling trend, with performance consistently improving from 3B to 7B parameters. Moreover, Edit-R1 delivers gains to editing models like FLUX.1-kontext, highlighting its effectiveness in enhancing image editing.

Hanzhong Guo, Jie Wu, Jie Liu +6

School of Computing and Data Science, The University of Hong Kong · ByteDance Seed · CUHK +1

Reward Modeling Reinforcement Learning RL for Diffusion Models RL for Image Editing

Apr 30, 2026cs.AI

PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations

Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining as supervised behavior cloning, overlooking the fundamental nature of robot learning as a goal-reaching process that requires understanding temporal task progress. We present \textbf{PRTS} (\textbf{P}rimitive \textbf{R}easoning and \textbf{T}asking \textbf{S}ystem), a VLA foundation model that reformulates pretraining through Goal-Conditioned Reinforcement Learning. By treating language instructions as goals and employing contrastive reinforcement learning, PRTS learns a unified embedding space where the inner product of state-action and goal embeddings approximates the log-discounted goal occupancy, the probability of reaching the language-specified goal from the current state-action, quantitatively assessing physical feasibility beyond static semantic matching. PRTS draws this dense goal-reachability supervision directly from offline trajectories without reward annotations, and folds it into the VLM backbone via a role-aware causal mask, incurring negligible overhead over vanilla behavior cloning. This paradigm endows the high-level reasoning system with intrinsic goal reachability awareness, bridging semantic reasoning and temporal task progress, and further benefits goal-conditioned action prediction. Pretrained on 167B tokens of diverse manipulation and embodied-reasoning data, PRTS reaches state-of-the-art performance on LIBERO, LIBERO-Pro, LIBERO-Plus, SimplerEnv, and a real-world suite of 14 complex tasks, with particularly substantial gains on long-horizon, contact-rich, and zero-shot novel-instruction settings, confirming that injecting goal-reachability awareness significantly improves both execution success and long-horizon planning of general-purpose robotic foundation policies.

Yang Zhang, Jiangyuan Zhao, Chenyou Fan +11

Institute of Artificial Intelligence (TeleAI), China Telecom · Tsinghua University · Shanghai Jiao Tong University +1

Reinforcement Learning Long-Horizon Robotic Manipulation Language-Conditioned Robot Manipulation Vision-Language-Action Models Contrastive RL Goal-Conditioned RL

Apr 30, 2026math.OC

Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms

This paper is a continuation work of Ren et al. (2026) aiming to further devise q-learning algorithms for mean-field control (MFC) with controlled common noise. Based on the relaxed control formulation, we first establish the martingale condition of the value function and the Iq-function by evaluating along the conditional state distributions generated by all test policies. As the data in the relaxed control formulation are not observable in practice, we quantify the error incurred when they are replaced by the observable ones in the exploratory formulation under discretely sampled actions. This, together with a two-layer fixed point characterization of an optimal policy in Ren et al. (2026), allows us to propose several algorithms including the Actor-Critic q-learning algorithm, in which the policy is updated in the Actor-step based on the iteration rule induced by the improved Iq-function, and the value function and Iq-function are updated in the Critic-step based on the martingale orthogonality condition using the data from the exploratory formulation. We also establish the convergence of the inner iterations in the Actor-step in an infinite-horizon linear quadratic (LQ) framework. In two examples, within and beyond LQ framework, our q-learning algorithms are implemented with satisfactory performance.

Zhenjie Ren, Xiaoli Wei, Xiang Yu +1

LaMME, Universit´e ´Evry Paris-Saclay, ´Evry, France · Department of Applied Mathematics, The Hong Kong Polytechnic University, Kowloon, Hong Kong · Department of Industrial Engineering and Operations Research, Columbia University, New York, USA

Reinforcement Learning Stochastic Optimal Control Q-Learning Continuous-Time RL Actor-Critic Methods Optimal Control

Apr 30, 2026cs.RO

Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction

Deep reinforcement learning (DRL) finds extensive application in autonomous drone navigation within complex, high-risk environments. However, its practical deployment faces a safety-exploration dilemma: soft penalty mechanisms encourage risky trial-and-error, while most constraint-based methods suffer degraded performance under sensor noise and intent uncertainty. We propose Dynamic-TD3, a physically enhanced framework that enforces strict safety constraints while maintaining maneuverability by modeling navigation as a Constrained Markov Decision Process (CMDP). This framework integrates an Adaptive Trajectory Relational Evolution Mechanism (ATREM) to capture long-range intentions and employs a Physically Aware Gated Kalman Filter (PAG-KF) to mitigate non-stationary observation noise. The resulting state representation drives a dual-criterion policy that balances mission efficiency against hard safety constraints via Lagrangian relaxation. In experiments with aggressive dynamic threats, this approach demonstrates superior collision avoidance performance, reduced energy consumption, and smoother flight trajectories.

Wentao Chen, Jingtang Chen, Mingjian Fu +4

Reinforcement Learning UAV Navigation Constrained RL Dynamic Obstacle Avoidance Trajectory Prediction

Apr 29, 2026cs.LG

AutoREC: A reinforcement learning platform for equivalent circuit model generation

This paper introduces AutoREC, an open-source Python platform for developing, training, and evaluating reinforcement learning (RL) agents that automatically generate equivalent circuit models (ECMs) from electrochemical impedance spectroscopy (EIS) data. Although ECMs are widely used to interpret EIS measurements, their identification typically relies on manual trial-and-error, requiring domain expertise and limiting scalability, particularly in autonomous experimental pipelines such as self-driving laboratories. In AutoREC, ECM generation is formulated as a Markov decision process in which an RL agent sequentially modifies a circuit topology based on the current state, available actions, and feedback from the resulting model. The platform supports an end-to-end workflow encompassing EIS preprocessing with selectable impedance representations, agent setup and training, ECM generation for new measurements, and visualization-based evaluation and analysis of agent decision-making. AutoREC implements a configurable Double Deep Q-Network (DDQN) agent with prioritized experience replay and a dedicated dead-loop mitigation strategy for navigating the complex circuit-generation action space efficiently. To demonstrate the platform, we trained and evaluated a representative agent on synthetic EIS datasets and applied it to previously unseen experimental spectra from battery, corrosion, oxygen evolution reaction, and CO

_2

reduction systems. These case studies illustrate the end-to-end capabilities of AutoREC while revealing challenges associated with experimental complexity and limited training-data coverage. The demonstrated agent serves as a reference implementation; AutoREC provides an extensible foundation through which users can develop and evaluate agents tailored to their specific electrochemical systems and research objectives.

Ali Jaberi, Yonatan Kurniawan, Robert Black +5

Clean Energy Innovation Research Centre, National Research Council Canada, Mississauga, ON, Canada · Department of Materials Science and Engineering, University of Toronto, Toronto, ON, Canada · Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada +1

Reinforcement Learning System Identification

Apr 29, 2026cs.RO

Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training

This paper presents a hierarchical decision-making framework for unmanned aerial vehicle (UAV) missions motivated by search-and-rescue (SAR) scenarios under limited simulation training. The framework combines a fixed rule-based high-level advisor with an online goal-conditioned low-level reinforcement learning (RL) controller. To stress-test early adaptation, we also consider a strict no-pretraining deployment regime. The high-level advisor is defined offline from a structured task specification and compiled into deterministic rules. It provides interpretable mission- and safety-aware guidance through recommended actions, avoided actions, and regime-dependent arbitration weights. The low-level controller learns online from task-defined dense rewards and reuses experience through a mode-aware prioritized replay mechanism augmented with rule-derived metadata. We evaluate the framework on two tasks: battery-aware multi-goal delivery and moving-target delivery in obstacle-rich environments. Across both tasks, the proposed method improves early safety and sample efficiency primarily by reducing collision terminations, while preserving the ability to adapt online to scenario-specific dynamics.

Mahya Ramezani, Holger Voos

Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg.

Reinforcement Learning UAV Navigation Hierarchical RL Safe RL Sample-Efficient RL Goal-Conditioned RL

Apr 29, 2026cs.LG

Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding

RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the rollout or optimization regime, for example, through off-policy execution, replay, or lower-precision generation. We study speculative decoding as a lossless acceleration primitive for RL rollouts that preserves the target model's output distribution. We implement speculative decoding in NeMo-RL with a vLLM backend, supporting both synchronous and asynchronous pipelines and enabling speculation during RL rollouts. This benefit is realizable across speculation mechanisms, such as pretrained MTP heads, small external draft models or even techniques such as Eagle3, which are traditionally applied after RL phase. This yields a deployment path for state-of-the-art speculative decoding inside RL training. In a reasoning post-training workload at 8B scale under synchronous RL, speculative decoding improves rollout throughput by 1.8x. Using a high-fidelity performance simulator, we project that combining speculative decoding with asynchronous RL yields up to 2.5x end-to-end training speedup at 235B scale.

Hayate Iso, Tiyasa Mitra, Sudipta Mondal +15

NVIDIA

Reinforcement Learning Speculative Decoding LLM Inference Acceleration RL Post-Training

Apr 29, 2026cs.AI

FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards

Live future prediction refers to the task of making predictions about real-world events before they unfold. This task is increasingly studied using large language model-based agent systems, and it is important for building agents that can continually learn from the real world. It can provide a large number of prediction questions grounded in diverse real-world events, while preventing answer leakage. To leverage the advantages of future prediction, we present FutureWorld, a live agentic reinforcement learning environment that closes the training loop between prediction, outcome realization, and parameter updates. Specifically, we modify and extend verl-tool, resulting in a new framework that we call verl-tool-future. Unlike standard reinforcement learning training frameworks that rely on immediate rewards, verl-tool-future stores prediction-time rollouts, backfills rewards after real-world outcomes become available, and then replays the completed trajectories for policy update. Across three open-source agents, successive FutureWorld training rounds lead to consistent improvements in prediction accuracy, probabilistic scoring, and calibration, demonstrating that delayed real-world outcome feedback can serve as an effective reinforcement learning signal.

Zhixin Han, Yanzhi Zhang, Chuyang Wei +11

College of Software, Nankai University · Zhongguancun Academy, Beijing, China · Academy of Mathematics and Systems Science, Chinese Academy of Sciences +3

Agentic RL Reinforcement Learning Probabilistic Forecasting RL for LLM Agents

Apr 29, 2026cs.LG

Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning

Offline reinforcement learning (RL) agents often fail when deployed, as the gap between training datasets and real environments leads to unsafe behavior. To address this, we present SAS (Self-Alignment for Safety), a transformer-based framework that enables test-time adaptation in offline safe RL without retraining. In SAS, the main mechanism is self-alignment: at test time, the pretrained agent generates several imagined trajectories and selects those satisfying the Lyapunov condition. These feasible segments are then recycled as in-context prompts, allowing the agent to realign its behavior toward safety while avoiding parameter updates. In effect, SAS turns Lyapunov-guided imagination into control-invariant prompts, and its transformer architecture admits a hierarchical RL interpretation where prompting functions as Bayesian inference over latent skills. Across Safety Gymnasium and MuJoCo benchmarks, SAS consistently reduces cost and failure while maintaining or improving return.

Seungyub Han, Hyungjin Kim, Jungwoo Lee

Seoul National University

Reinforcement Learning Offline RL Safe RL

Apr 29, 2026cs.LG

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking

Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy. Existing approaches address these uncertainty sources in isolation - epistemic uncertainty is used to guide exploration, while preference uncertainty is absorbed during reward model training but discarded during policy optimization. We introduce Uncertainty-Aware Reward Discounting (UARD), a principled framework that jointly models epistemic uncertainty in value estimation via ensemble disagreement and aleatoric uncertainty in human preference annotations via annotator variability, combining these signals through a confidence-adjusted Reliability Filter that adaptively modulates reward weighting during policy optimization. We prove that this dynamic discounting preserves the contraction property of the Bellman operator, guaranteeing convergence to a unique fixed point, and provide an information-theoretic justification grounded in the Information Bottleneck principle. Empirically, UARD reduces reward hacking incidents by up to 93.6% across discrete decision-making and continuous control benchmarks (MuJoCo) compared to nine baselines including DQN, Ensemble-DQN, CQL, CPO, TRPO, SAC, EDAC, SUNRISE, and PPO, while maintaining competitive task performance on well-specified rewards. Under annotation noise ranging from 10% to 30% Gaussian perturbation, UARD retains near-zero safety violations compared to baselines' near-linear degradation. These results demonstrate that treating uncertainty as an active component of the optimization objective - rather than a passive diagnostic signal - provides a principled pathway toward more reliable and aligned RL systems.

Disha Singha

Reward Hacking Reinforcement Learning Aleatoric Uncertainty Safe RL RL from Human Feedback

Apr 29, 2026cs.LG

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control

Reinforcement learning (RL) has enabled complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performance saturation, preventing continued gains as RL training scales. This problem can be characterized by the collapse of entropy, a key diagnostic for exploration in RL. Existing attempts focus on preventing entropy collapse through regularization or clipping. However, their resulting entropy curves often exhibit instability in the long term, which hinders performance gains. In this paper, we introduce Entrocraft, a simple rejection-sampling approach that realizes user-customized entropy schedule by biasing the advantage distributions. Entrocraft requires no objective regularization and is advantage-estimator-agnostic. Theoretically, we relate per-step entropy change to the advantage distribution under minimal assumptions. This explains the behavior of existing RL and entropy-preserving methods. Entrocraft also enables a systematic study of entropy schedules, which reveals that linear annealing, which starts high and decays to a slightly lower target, performs best. Empirically, Entrocraft addresses performance saturation, significantly improving generalization, output diversity, and long-term training. It enables a 4B model to outperform an 8B baseline, sustains improvement for up to 4x longer before plateauing, and raises pass@K by 50% over the baseline.

Bolian Li, Yifan Wang, Yi Ding +3

Purdue University, West Lafayette, IN, USA

RL for Language Models Reinforcement Learning RL for Language Model Reasoning Maximum Entropy RL RL Post-Training

Apr 29, 2026cs.LG

DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training

Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model performance block the entire training pipeline. Asynchronous training offers a natural remedy by overlapping generation with training, but introduces a fundamental tension between efficiency and algorithmic correctness. We identify three constraints in asynchronous training to preserve convergence: intra-trajectory policy consistency, data integrity, and bounded staleness. Existing approaches fail to intrinsically address the long-tailed trajectory problem, which is further exacerbated by the imbalance characteristic of Mix-of-Experts models, or deviate from the standard RL training formulation, thereby hindering model convergence. Therefore, we propose DORA (Dynamic ORchestration for Asynchronous Rollout), which addresses this challenge through algorithm-system co-design. DORA introduces multi-version streaming rollout, a novel asynchronous paradigm that maintains multiple policy versions concurrently -- simultaneously achieving full bubble elimination without compromising algorithmic constraints. Experimental results demonstrate that our DORA system achieves substantial improvements in throughput -- up to 2--3 times higher than state-of-the-art systems on open-source benchmarks -- without compromising convergence. Furthermore, in large-scale industrial applications with tens of thousands of accelerators, DORA accelerates RL training by 2--4 times compared to synchronous training across various scenarios. The resultant open-source models, LongCat-Flash-Thinking, exhibit competitive performance on complex reasoning benchmarks, matching the capability of most advanced LLMs.

Tianhao Hu, Xiangcheng Liu, Youshao Xiao +15

Meituan, China

RL for Language Models Asynchronous RL Reinforcement Learning RL Post-Training LLM Training

Apr 28, 2026cs.LG

How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum

SFT-then-RLVR is widely used for post-training reasoning models, but why this specific ordering, and why RLVR-only stalls at cold start, have lacked a unifying theoretical account. We provide that account under a unified loss family

J_Q

using the Tsallis

q

-logarithm.

J_Q

is a single-parameter family that interpolates between RLVR (at

q{=}0

, the \textit{exploitation pole}) and the log-marginal-likelihood over latent trajectories (at

q{=}1

, the \textit{density-estimation pole}), under which the standard pipeline corresponds to a stepwise

q{=}1 \to 0

schedule. All members share the same per-example gradient direction, differing only by a per-instance amplification

P_θ^{-q}

that reweights each instance independently of the learning rate. Under gradient flow analysis, we show that the exploitation pole requires

Ω(\frac{1}{p_0})

time to escape cold start but is robust to label noise, while the density-estimation pole escapes in

Θ\big(\log(\frac{1}{p_0})\big)

but memorizes label noise. This separation explains how SFT (

q{=}1

) first moves the model out of the cold-start regime, followed by the more robust RLVR (

q{=}0

), under the SFT-then-RLVR paradigm. We further derive two Monte Carlo estimators that directly optimize fixed-

q

on the

J_Q

continuum, without annotated rationales: Gradient-Amplified RL (GARL) and Posterior-Attenuated Fine-Tuning (PAFT), with shared bias

O\big(\frac{q}{M P_θ^q}\big)

but different variance and stability properties. On FinQA, HotPotQA, and MuSiQue, GARL at sufficiently high

q

substantially mitigates cold-start stalling, escaping cold start where GRPO fails entirely. In warm start, GARL at low

q

dominates FinQA where training is stable; on HotPotQA and MuSiQue, GARL destabilizes and PAFT at

q{=}0.75

remains stable, reaching

47.9

\texttt{m@16} on HotPotQA (

+13.9

over GRPO).

Chu-Cheng Lin, Eugene Ie

Google

Supervised Fine-Tuning Reinforcement Learning RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards

Apr 28, 2026cs.AI

Sample-efficient Neuro-symbolic Proximal Policy Optimization

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal Policy Optimization (PPO) that transfers partial logical policy specifications learned in easier instances to guide learning in more challenging settings. We introduce two integrations of symbolic guidance: (i) H-PPO-Product, which biases the action distribution at sampling time, and (ii) H-PPO-SymLoss, which augments the PPO loss with a symbolic regularization term. We evaluate our methods on three benchmarks (OfficeWorld, WaterWorld, and DoorKey), showing consistently faster learning and higher return at convergence than PPO and a Reward Machine baseline, also under imperfect symbolic knowledge.

Simone Murari, Celeste Veronese, Daniele Meli

Dept. of Computer Science, University of Verona, Italy

Reinforcement Learning Proximal Policy Optimization Sparse-Reward RL Policy Learning Sample-Efficient RL

Apr 28, 2026cs.AI

Improving Zero-Shot Offline RL via Behavioral Task Sampling

Offline zero-shot reinforcement learning (RL) aims to learn agents that optimize unseen reward functions without additional environment interaction. The standard approach to this problem trains task-conditioned policies by sampling task vectors that define linear reward functions over learned state representations. In most existing algorithms, these task vectors are randomly sampled, implicitly assuming this adequately captures the structure of the task space. We argue that doing so leads to suboptimal zero-shot generalization. To address this limitation, we propose extracting task vectors directly from the offline dataset and using them to define the task distribution used for policy training. We introduce a simple and general reward function extraction procedure that integrates into existing offline zero-shot RL algorithms. Across multiple benchmark environments and baselines, our approach improves zero-shot performance by an average of 20%, highlighting the importance of principled task sampling in offline zero-shot RL.

Nazim Bendib, Nicolas Perrin-Gilbert, Olivier Sigaud

Institut des Systèmes Intelligents et de Robotique, ISIR, Sorbonne Université, Paris, France.

Reinforcement Learning Offline RL Multi-Task RL Generalization in RL Goal-Conditioned RL

Apr 28, 2026cs.CV

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

Recent image editing models have achieved strong visual fidelity but often struggle with tasks requiring complex reasoning. To investigate and enhance the reasoning-grounded planning for image editing, we propose DDA-Thinker, a Thinker-centric framework designed for the independent optimization of a planning module (Thinker) over a fixed generative model (Editor). This decoupled Thinker-centric paradigm facilitates a controlled analysis of the planning module and makes its contribution under a fixed Editor easier to assess. To effectively guide this Thinker, we introduce a dual-atomic reinforcement learning framework. This framework decomposes feedback into two distinct atomic rewards implemented through verifiable checklists: a cognitive-atomic reward to directly assess the quality of the Thinker's executable plan, which serves as the actionable outcome of the Thinker's reasoning, and a visual-atomic reward to assess the final image quality. To improve checklist quality, our checklist synthesis is grounded not only in the source image and user instruction but also in a rational reference description of the ideal post-edit scene. To support this training, we further develop a two-stage data curation pipeline that first synthesizes a diverse and reasoning-focused dataset, then applies difficulty-aware refinement to curate an effective training curriculum for reinforcement learning. Extensive experiments on reasoning-driven image editing benchmarks, including RISE-Bench and KRIS-Bench, demonstrate that our approach substantially improves overall performance. Our method enables a community model to achieve results competitive with strong proprietary models, highlighting the practical potential of Thinker-centric optimization under a fixed-editor setting.

Hanqing Yang, Qiang Zhou, Yongchao Du +6

Alibaba Group · Zhejiang University

Reinforcement Learning Text-Guided Image Editing RL for Generative Models Image Editing RL for Image Editing

Apr 28, 2026cs.LG

Safe-Support Q-Learning: Learning without Unsafe Exploration

Ensuring safety during reinforcement learning (RL) training is critical in real-world applications where unsafe exploration can lead to devastating outcomes. While most safe RL methods mitigate risk through constraints or penalization, they still allow exploration of unsafe states during training. In this work, we adopt a stricter safety requirement that eliminates unsafe state visitation during training. To achieve this goal, we propose a Q-learning-based safe RL framework that leverages a behavior policy supported on a safe set. Under the assumption that the induced trajectories remain within the safe set, this policy enables sufficient exploration within the safe region without requiring near-optimality. We adopt a two-stage framework in which the Q-function and policy are trained separately. Specifically, we introduce a KL-regularized Bellman target that constrains the Q-function to remain close to the behavior policy. We then derive the policy induced from the trained Q-values and propose a parametric policy extraction method to approximate the optimal policy. Our approach provides a unified framework that can be adapted to different action spaces and types of behavior policies. Experimental results demonstrate that the proposed method achieves stable learning and well-calibrated value estimates and yields safer behavior with comparable or better performance than existing baselines.

Yeeun Lim, Narim Jeong, Donghwan Lee

HD Korea Shipbuilding & Offshore Engineering · Department of Electrical Engineering, KAIST, Daejeon, South Korea

Reinforcement Learning KL-Regularized RL Q-Learning RL Exploration Safe RL

Apr 28, 2026cs.AR

How Can Reinforcement Learning Achieve Expert-level Placement?

Chip placement is a critical step in physical design. While reinforcement learning (RL)-based methods have recently emerged, their training primarily focuses on wirelength optimization, and therefore often fail to achieve expert-quality layouts. We identify the reward design as the primary cause for the performance gap with experts, and instead of formalizing intricate processes, we circumvent this by directly learning from expert layouts to derive a reward model. Our approach starts from the final expert layouts to infer step-by-step expert trajectories. Using these trajectories as demonstrations or preferences, we train a model that captures the latent implicit rewards in expert results. Experiments show that our framework can efficiently learn from even a single design and generalize well to unseen cases.

Ruo-Tong Chen, Ke Xue, Chengrui Gao +7

State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · Huawei Noah’s Ark Lab, China

Reinforcement Learning Electronic Design Automation Reward Design for RL

Apr 28, 2026cs.LG

Model-Aware Data Cleaning for Tabular Foundation Models

Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets, but their in-context learning assumes approximately clean inputs: real- world missing values, outliers, and duplicates create a prior mismatch that degrades both accuracy and calibration. We study reinforcement learning for tabular data cleaning, a learned policy that sequences cleaning operators and introduce L2C-TFM with a model-aware reward (TFMAwareReward). We are explicit about what this reward optimizes: it regularizes the Wasserstein distance between the cleaned and the original (dirty) data, a distributional-stability term, which we measure as a diagnostic. Across six experiments on ten OpenML datasets: (i) three of seven reward designs collapse to degenerate strategies, so reward engineering is non-trivial; (ii) under an 8-seed repeated-holdout protocol the model-aware reward matches a random-forest-reward baseline on accuracy (p=0.38), with a benefit confined to minority-class macro-F1 under class imbalance that is partly a reward-agnostic calibrated-threshold effect; and (iii) a policy pre-trained on one dataset transfers to held-out datasets. A diagnostic analysis shows that the two distances are distinct objectives: cleaning tends to move data away from the prior, and prior-distance, not distance-to-dirty, is what tracks downstream quality. We therefore treat prior alignment as a motivating objective and a target for future work, not a property of the reward evaluated here. Code, datasets, and the nested evaluation harness are available at https://github.com/LaureBerti/Learn2Clean/tree/master/Learn2Clean_TFM.

Laure Berti-Equille

IRD, ESPACE-DEV Montpellier, France

Tabular Foundation Models Reinforcement Learning