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

Sep 1, 2026cs.LG

Provably Safe Sim-to-Real Transfer

To mitigate the sample complexity of real-world reinforcement learning (RL), a common practice is to first train a policy in a simulator, where samples are cheap, and then deploy the learned policy in the real world with the hope that it generalizes effectively. Such direct sim-to-real transfer is not guaranteed to succeed: simulator-trained policies can be suboptimal in the real world due to sim-to-real mismatch. Correcting this mismatch requires collecting data from the real system, but in many applications, such as robotics and healthcare, this data-collection process is itself subject to safety constraints. This gives rise to the problem of safe sim-to-real transfer: how can an agent exploit an imperfect simulator while ensuring safe real-world data collection and learning a near-optimal feasible policy for the target system? We address this problem by formulating safe sim-to-real transfer within the framework of reward-free safe RL. We design a computationally efficient algorithm that exploits simulator information to provably reduce real-world interaction while ensuring safe exploration and enabling the computation of a near-optimal feasible policy for any potential reward function. Our real-world sample complexity bound characterizes the benefit of using the simulator in terms of the sim-to-real mismatch.

Tingting Ni, Maryam Kamgarpour

SYCAMORE, EPFL

Reinforcement Learning Sim-to-Real Transfer Reward-Free RL Safe RL Sample-Efficient RL

Sep 1, 2026cs.CL

CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs

Entity matching (EM) requires fine-grained contextual understanding and domain knowledge. Recent work shows that large language models (LLMs) can serve as strong matchers across domains, but most methods either make independent pairwise decisions or rely on manually designed composite pipelines, thus lacking flexibility in realistic multi-candidate settings. At the same time, they typically ignore inference cost at scale. We formulate LLM-based EM with candidates as a cost-aware sequential decision problem and propose CaRL-EM, a reinforcement learning controller that manages LLM operations. Given the state of an anchor record, its candidate set, and the cost, CaRL-EM adaptively chooses among different operators (Match/Compare/Select/Decide) and model capacities to maximize a quality-cost objective. The policy interacts with abstract operators, allowing the same controller to be reused with different underlying LLM backends at inference time without retraining. Experiments on 7 benchmarks show that CaRL-EM (i) learns to dynamically plan the usage of inexpensive and expensive operators based on task complexity, (ii) achieves robust zero-shot transfer across diverse datasets and domains, and (iii) consistently achieves a better quality-cost trade-off than strong LLM-based baselines and manually designed pipelines, yielding a lower inference cost at comparable or higher quality.

Chaohui Guo, Michel Klein, Zhisheng Huang

Department of Computer Science, Vrije Universiteit Amsterdam, Netherlands

Reinforcement Learning LLM Inference Scheduling Cost-Aware Inference

Sep 1, 2026cs.LG

Reinforcement Learning and Rule-Based Peer-to-Peer Pricing in Residential PV-BES Communities

This paper compares rule-based and learning-based pricing mechanisms for peer-to-peer (P2P) electricity trading in residential photovoltaic communities. The rule-based benchmarks comprise bill-sharing as an ex post allocation mechanism, the mid-market rate, and supply-demand-ratio pricing. The reinforcement-learning (RL) formulation is implemented through a Deep Q-Network and evaluated under multiplier-based and learnable SDR-shaped pricing, with a fixed-parameter SDR variant as a non-learning control. Performance is assessed through community savings together with complementary financial and operational indicators. In the base PV-only configuration, the rule-based benchmarks outperform the best RL policy. With battery energy storage, evaluated for the RL policies only, community savings under the best RL policy increase from EUR 734.23 to EUR 978.52. Across the learning-based modes and in both configurations, SDR-shaped pricing outperforms the multiplier-based parameterization considered. The results indicate that rule-based pricing remains highly competitive wherever the two families are compared directly, and that storage substantially improves the learning-based outcomes under this accounting, while the distribution of benefits remains heterogeneous across households.

Pablo Benalcazar, Maciej Kalka, Wilian Guamán +1

Division of Energy Economics, Mineral and Energy Economy Research Institute, Polish Academy of Sciences, Kraków, Poland · GITEA, Escuela Superior Politécnica de Chimborazo (ESPOCH), Riobamba, Ecuador

Reinforcement Learning Dynamic Pricing Power Systems

Sep 1, 2026cs.CL

Dense Process Supervision for Search Agents via Fact Utility Estimation

Reinforcement learning (RL) for search agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due to the unclear value of intermediate steps. It is hard to separate their contributions from the final result. In this paper, we propose a dense process supervision method based on fact utility estimation, which models the reasoning process as the accumulation of discrete evidence facts. We first extract structured facts from raw observations and organize them into an explicit fact store. To support credit assignment, we then cluster semantically equivalent facts and infer the posterior utility of each fact cluster using Bayesian estimation over group rollouts. Finally, we convert the estimated fact utilities into dense step-level rewards to guide RL training. Experiments on seven single-hop and multi-hop QA benchmarks show that our method consistently outperforms existing baselines. Ablation studies validate clear relative improvements on multi-hop QA compared to outcome reward-only training.

Rongzhi Zhu, Xiangyu Liu, Yi Liu +7

State Key Laboratory for Novel Software Technology, Nanjing University, China · Ant Group, China · National Institute of Healthcare Data Science, Nanjing University, China

Reinforcement Learning Credit Assignment in RL Step-Level Credit Assignment in RL Dense Reward RL Question Answering Process Supervision+1

Sep 1, 2026cs.IR

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

Retrieval is the first stage of modern search and advertising systems, selecting a candidate set from a large item universe for downstream ranking and auction. Recent work increasingly leverages LLMs to improve retrieval through query expansion, data synthesis, and retrieval-feedback training. However, the generative component is typically used for query-side augmentation, while final matching is still delegated to a downstream retriever. We introduce CoGR, a retrieval framework that instead trains LLMs to directly construct retrieval representations on both query and item sides. Each generator produces a compact set of keywords, which are matched directly through an inverted index, preserving compatibility with existing keyword-based retrieval infrastructure. CoGR uses a two-stage training pipeline. Supervised fine-tuning first establishes an aligned keyword space, after which co-evolving reinforcement learning alternately optimizes the query- and item-side generators with GRPO against the opposite side's frozen index. Both sides optimize the same query-to-item retrieval

F_1

objective: the query side receives retrieval

F_1

directly, while the item side receives a counterfactual marginal reward measuring the change in query-side

F_1

caused by its generated keywords. Across 10 representative sparse, dense, and generative baselines, CoGR achieves the best performance on both an internal APP Marketplace dataset and the public WANDS benchmark, improving

F_1

over the strongest baseline by

10.9\%

and

36.1\%

, respectively. Further analysis shows stable co-evolution and increasingly aligned query--item keyword spaces over training.

Runpeng Dai, Kaili Huang, Changsung Kang +1

University of North Carolina at Chapel Hill · Apple

Reinforcement Learning Generative Retrieval Lexical Retrieval RL for IR

Sep 1, 2026cs.GT

Independent Reinforcement Learning in Discounted Markov Games

In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming ``

\mathsf{ETH}

for

\mathsf{PPAD}

", we show that, for every fixed discount factor, there is no polynomial-time algorithm for computing inverse-polynomially accurate coarse correlated equilibria in discounted general-sum Markov games when players learn independently in decentralized settings. Complementing this hardness result, we provide what appears to be the first \emph{radically uncoupled} algorithm with sub-exponential convergence guarantees to coarse correlated equilibria in discounted general-sum Markov games without imposing any structural restrictions on the game. Our algorithm is a \emph{layered} variant of optimistic mirror descent with an increasing step-size schedule tailored to the multi-agent setting. Finally, we develop both full-feedback and partial feedback versions of the aforementioned algorithm and establish sub-exponential convergence guarantees for each case.

Asrin Efe Yorulmaz, Ugur Aydin, Tamer Basar

Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, 61801, USA

Reinforcement Learning Game Theory Decentralized Learning Mirror Descent Decentralized MARL

Aug 31, 2026stat.ML

Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost

We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achieve strong regret guarantees, they typically require sharing raw trajectories. This reliance incurs a communication cost that scales linearly with the number of episodes and violates the privacy constraints of federated settings. To address these limitations, we propose Fed-LSVI, the first provably efficient federated algorithm for online reinforcement learning with linear function approximation in episodic Markov decision processes. By integrating a determinant-based event-triggered synchronization with a stepwise backward update mechanism, Fed-LSVI enables agents to collaboratively learn an optimal policy by exchanging only compressed sufficient statistics. We prove that Fed-LSVI achieves a regret bound of

\widetilde{\mathcal O}(\sqrt{Md^3H^4T})

, where

d

is the feature dimension,

H

is the horizon length,

M

is the number of agents, and

T

is the number of episodes per agent, matching the best-known regret for multi-agent online reinforcement learning with linear function approximation. Moreover, by following the stringent communication and privacy constraints of the federated setting, Fed-LSVI reduces the communication cost to only logarithmic dependence on

T

, representing a significant improvement over prior methods.

Zihang Liang, Haochen Zhang, Lingzhou Xue

Department of Statistics, The Pennsylvania State University

Reinforcement Learning Federated RL Multi-Agent Reinforcement Learning Federated Learning

Aug 31, 2026cs.AI

Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence

Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress to open-ended and agentic tasks remains difficult because reliable rewards are harder to obtain and direct human supervision cannot keep pace with the scale and complexity of model-generated experience. This paper studies how LRMs can continue to improve as human supervision gradually recedes from the learning loop. We examine two connected dimensions of this problem. The reward axis traces the development from per-instance human judgments to reusable verifiers and rewards that operate even without human feedback. The experience axis examines how learning can progress from human-curated tasks and environments toward self-generated curricula, constructed environments, and autonomous co-evolution. We connect these dimensions through a five-level ladder from L0 to L4 that identifies which parts of the learning process remain under continued human control. Our analysis further highlights the risks introduced by increasingly autonomous rewards and experience generation, including reward hacking, feedback drift, curriculum collapse, and environment errors. Consequently, we also provide the evaluation around three complementary objects: policy capability, feedback fidelity, and experience quality. This analysis provides a structured account of current approaches to scaling LRMs beyond human supervision and the open problems involved in developing self-sustaining learning systems toward superintelligence. Furthermore, we maintain a continuously updated GitHub repository to track the latest advances.

Zhiqin Yang, Jingwen Fu, Yuhan Liu +16

The Hong Kong University of Science and Technology · Zhongguancun Academy · Xi’an Jiaotong University +6

Reinforcement Learning RL for Language Model Reasoning Curriculum RL Reinforcement Learning with Verifiable Rewards Language Model Self-Improvement Large Reasoning Models

Aug 31, 2026cs.LG

Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL

While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale over which actions should be modeled. Departing from the standard formulation relying on single-step actions, we extend contrastive reinforcement learning (CRL), a prototypical self-supervised method, to operate over action chunks, and find that this results in large, pervasive gains across established offline and online benchmarks: +31.7% and +93.1% across 18 and 11 environments respectively. While action-chunking-driven gains are generally explained through the ability to model non-Markovian, temporally extended policies, and to propagate unbiased multi-step returns, interestingly, we find that these arguments only partially apply to CRL. Our empirical studies suggest that, in the context of CRL, an action chunk carries more information about the goal than a single action, measurably improving the critic's representations, and rendering the algorithm significantly more effective.

Michal Korniak, Kamil Dybek, Benjamin Eysenbach +2

ETH Zurich · University of Warsaw · Princeton University +3

Reinforcement Learning Offline RL Representation Learning for RL Contrastive RL

Aug 31, 2026cs.LG

Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic

Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level policy, its use at test time may introduce practical subgoal management difficulties. An alternative paradigm utilizes a high-level planner to assist learning, while the policy remains conditioned only on the final goal, enabling planner-free deployment. Among these methods, Reinforcement Learning with Imagined Subgoals (RIS) introduces a regularization term that encourages the policy to take the same actions for the final goal as it does for an intermediate goal. This regularization, however, may lead to goal-chaining issues when intermediate goals are low-dimensional. Potential-based reward shaping (PBRS) translates plans into an additional reward while ensuring that the optimal policy remains unchanged. Yet, it can generate deceptive rewards in terminal states. We study these failure cases and first propose an alternative reward shaping method (RS) that removes these deceptive rewards at the expense of theoretical guarantees of PBRS. Similar to this RS variant, we then propose another method named Locally-Guided Actor Critic (LG-AC) that rewards the agent for reaching intermediate goals. Unlike RS, where intermediate rewards are implicit in the shaping signal, we explicitly condition a value estimator on the full sequence of intermediate goals but represent the value function as a sum of subgoal-conditioned value functions, enabling dense hindsight relabeling. We evaluate all these methods in tasks with challenging goal-chaining requirements and empirically highlight specific cases in which either action regularization or reward shaping yield low performance, while LG-AC achieves the best overall performance across tasks.

Olivier Serris, Stéphane Doncieux, Olivier Sigaud

ISIR · Sorbonne Université, CNRS

Reinforcement Learning Sparse-Reward RL Actor-Critic Methods Reward Design for RL Goal-Conditioned RL

Aug 31, 2026cs.LG

BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement Learning

Expected-cost constraints can still permit rare, high-cost events. Monte Carlo conditional value at risk (CVaR) gradients can be noisy at high confidence, whereas critics that model an outcome distribution add complexity. We propose BCPPO (Bachelier-Inspired Constrained Proximal Policy Optimization), a proximal policy optimization (PPO) method. Separately initialized cost-prediction networks (critics), trained with random sample masks, produce disagreement that marks predictions sensitive to which state-action regions occur in the training data and to critic training. A Bachelier formula for the expected amount above a reference level converts this disagreement into a smooth policy-update penalty. Gradients from this penalty do not alter the critics, so temporal-difference (TD) critic learning is unchanged. A saturation-aware controller adjusts the mean-cost penalty and stops accumulated error from growing while that penalty is clipped. Deployment retains only the policy network. The disagreement penalty is neither a tail-event probability nor a guaranteed error bound, and it provides no safety guarantee. Across 175 runs with shared tasks, costs, budgets, training steps, and evaluation seeds, no comparator attains both higher mean return and lower mean CVaR than BCPPO in any task. On Push1, BCPPO has no lower return and no higher CVaR than every comparator, with at least one strict gain. These results support a practical balance among reward, caution around cost predictions that vary across trained critics, and policy-only deployment.

Dongsheng Hou, Yanqiao Chen, Yuhan Rui

Southern University of Science and Technology

Reinforcement Learning Constrained RL Proximal Policy Optimization Safe RL Conditional Value-at-Risk

Aug 31, 2026cs.LG

Reinforcement Learning for Symbolic Equation Solving

We present a reinforcement-learning agent that solves symbolic equations step by step, covering both nonlinear closed equations (radicals, exponentials, trigonometric) and a controlled class of restricted-open families requiring a change of variables (CoV) such as completing the square. We cast algebra as an MDP with a dynamic action space and a tree-structured policy (TreeMLP). The main policy learns from reward alone with no supervised solution traces; the CoV substitution comes from a supervised generator interchangeable with a CAS call. On closed equations the agent matches the prior best on CommonCore (0.93 greedy vs. ConPoLe's 0.925) under a single policy. On four hand-designed restricted-open families (quadratic, cubic, quartic, exponential) it reaches 0.79 beam / 0.67 greedy, exceeding the strongest non-learned search (A-star, 0.64). Learned CoV timing has content only on the exponential family, the one requiring a nested CoV, where a natural rule solves none of the held-out equations while the policy solves 75% from reward alone. At 10x scale a sharp seed-level bimodality emerges; a UCB learning-progress curriculum shows a non-significant positive trend toward mitigating it. We do not claim general open-equation solving: every open-equation result is confined to these four controlled families.

Kevin P O Keeffe

Starling Research Institute

Reinforcement Learning Neurosymbolic Learning

Aug 30, 2026cs.LG

Uncertainty-Driven Replay Memory for Reinforcement Learning

Uncertainty estimation provides promising capabilities for reinforcement learning (RL) agents. Notably, estimating uncertainty can reduce the training time and enable agents to obtain greater rewards over time by exploiting information related to whether an action would facilitate exploration of portions of an environment that are well-known versus those that are relatively unknown. In this work, we propose a novel formulation of the experience replay buffer commonly used in RL that we call uncertainty-driven replay memory (UDRM), which entails an update scheme for internally stored memories based on uncertainty estimates obtained by an RL model during training. In contrast to existing forms of RL, which typically use temporal difference error or the distribution of transitions to update the replay memory buffer and train RL controllers, our scheme biases the memory buffer to store more uncertain transitions that will improve an RL agent's generalization throughout training. Experimental results demonstrate that our proposed uncertainty-aware replay buffer enables an RL agent to obtain higher rewards during training compared to other existing uncertainty-aware RL frameworks.

Sheeraja Rajakrishnan, Alexander G. Ororbia, Travis Desell +1

Rochester Institute of Technology

Reinforcement Learning Generalization in RL

Aug 30, 2026cs.RO

SmoothRL: Online Reinforcement Learning During Asynchronous Execution

Deploying robot policies in the physical world requires satisfying two fundamental desiderata: reliability and smooth real-time execution. However, deploying state-of-the-art generalist models presents challenges on both fronts. Achieving the precision and robustness required for real-world deployment necessitates sample-efficient online reinforcement learning (RL) to adapt pretrained models. Meanwhile, the increasing scale of robot foundation models has led to higher inference latency. To satisfy real-time constraints under high latency, modern systems adopt asynchronous inference with action chunking, overlapping policy computation with chunk execution to hide latency and enable smooth control. Despite their complementary roles, integrating asynchronous execution with gradient-based online RL remains underexplored. We present SmoothRL, an online RL framework that fine-tunes a pretrained policy within an asynchronous inference loop. SmoothRL follows a value-gradient paradigm, directly updating policy parameters using gradients of the action-value function with respect to policy actions. To enable correct optimization under asynchronous execution, SmoothRL explicitly models the asynchronous inference process during training. Specifically, each generated action chunk is partitioned by frame index into three regions: a committed region, consisting of actions committed by the previous inference cycle; an execution region, containing newly generated actions executed by the robot; and a discarded region, containing actions superseded by the next inference cycle. Gradients are propagated only through the execution region, ensuring policy optimization aligns with the trajectory distribution induced by asynchronous execution. We evaluate SmoothRL on real-world robotic tasks requiring high precision, as well as highly dynamic tasks that necessitate asynchronous execution.

Guang Gao, Yuxuan Nong, Baifu Huang +1

Astribot Team

Robot Policy Learning Asynchronous RL Reinforcement Learning Robotic RL

Aug 20, 2026cs.CV

RIPE++: Reinforced Keypoint Learning from Positive Pairs Only

Sparse keypoint extraction and matching underpin core tasks in geometric computer vision, including structure-from-motion, visual SLAM, augmented reality, and medical image registration. Learning robust local feature representations, however, typically requires accurate camera poses or depth supervision, which are often unavailable in real-world settings. Reinforcement learning (RL) has recently emerged as a promising alternative, requiring only the information if two images show the same scene or not. However, existing RL formulations such as RIPE rely on coarse binary rewards and carefully constructed negative training pairs, limiting training stability and descriptor discriminability. In this paper, we revisit RL-based keypoint learning and propose a reward that fully exploits the geometric consistency signal, deriving both reward and penalty from a single positive pair without contrasting against negatives. This richer signal provides sufficient supervisory contrast to learn discriminative detectors and descriptors from positive image pairs alone, enabling representation learning under extremely limited supervision. Furthermore, we show that the same RL objective can be extended to the matching stage by adapting LightGlue, raising AUC@5 on MegaDepth1500 from 56.58 to 59.65 and enabling weakly-supervised training of the full sparse matching pipeline from image pairs with partial visual overlap. We validate our approach on established benchmarks, demonstrating competitive results compared to fully-supervised methods. We further show that the method can be even trained on low texture medical video sequences, where camera poses are usually unavailable and standard SfM pipelines often fail. Code and data are available at https://github.com/fraunhoferhhi/RIPEpp .

Johannes Künzel, Peter Eisert, Anna Hilsmann

Fraunhofer Heinrich-Hertz-Institute, HHI, Germany · Humboldt University Berlin, Germany

Representation Learning Reinforcement Learning Image Matching Keypoint Detection Self-Supervised Visual Representation Learning

Aug 19, 2026cs.AI

RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training

Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct iterative search beyond single-turn settings. Yet multi-turn RL training remains highly unstable, often causing severe performance degradation as the number of turns increases. Through theoretical analysis, we identify three tightly coupled sources of instability: rollout-training context mismatch, weak turn-level credit assignment under sparse terminal rewards, and asynchronous policy drift when short and long trajectories are optimized under different policy versions. We show that these issues share a common structural origin in flattened trajectory optimization and address them through a unified reverse-turn formulation. We propose Reverse-Turn Policy Optimization (RTPO), which organizes multi-turn rollouts as sparse reverse trees and performs turn-level policy updates in temporal reverse order, aligning each decision with its downstream continuation. RTPO enables causally consistent turn-level credit assignment and on-policy continuation to control asynchronous drift. We provide theoretical guarantees showing that RTPO eliminates context mismatch and asynchronous drift under the proposed turn-level formulation, reduces credit bias, and converges to recursive optimality. Experiments on multi-turn agentic RL benchmarks show that RTPO improves upon trajectory- and turn-level baselines by 21.50% and 10.76%, respectively, highlighting its potential to support more stable training for tool-using agents.

Yugu Li, Zehong Cao, Jianglin Qiao +1

School of CSIT · ACFR · School of EECMS

Agentic RL Reinforcement Learning Policy Optimization Temporal Credit Assignment RL for Tool Use

Aug 13, 2026cs.AI

OGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways

Heterogeneous USV cooperative pursuit in constrained port waterways requires evader interception under navigation, traffic, and role constraints. This paper proposes OGR-MARL, an option-guided residual multi-agent reinforcement learning framework that is decoupled from a specific MARL algorithm. OGR-MARL integrates shared evader belief, role-conditioned option targets, adaptive rule penalties, and residual policy learning, allowing different MARL algorithms to learn corrective actions on top of rule-guided behaviors rather than exploring constrained port environments from scratch. We instantiate OGR-MARL with representative continuous-control MARL backbones, including MADDPG, MATD3, MAPPO, and MASAC, yielding OGR-MADDPG, OGR-MATD3, OGR-MAPPO, and OGR-MASAC. Experiments in an abstract Xiazhimen port-waterway scenario show that the OGR-MASAC instantiation achieves a 75.0% capture rate, promising mission-effective rule compliance, and the best heterogeneous coordination among the tested methods. Without retraining, zero-shot transfer to a QGIS/AIS-informed Xiazhimen map achieves promising results, demonstrating the generalization potential of OGR-MARL in more complex port scenarios.

Mao Jiayang, Wang Lanfeng, Peng Zhao-Han

College of Information Engineering Sichuan Agricultural University Yaan, China · Shenzhen International Graduate School Tsinghua University Shenzhen, China

Reinforcement Learning Mobile Robotics Multi-Agent Systems Residual Policy Learning Cooperative MARL Multi-Agent Reinforcement Learning+2

Aug 13, 2026stat.ML

Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

In this paper, we study how to perform statistical inference for quantile temporal difference learning (QTD) in distributional reinforcement learning. Assuming access to a generative model, we first establish functional central limit theorems for both synchronous and asynchronous QTD, which show that the averaged iterates of QTD converge weakly to a rescaled Brownian motion. We next provide online inference methods. Based on random scaling, the inference procedure constructs an asymptotically pivotal statistic for inference by using the information along the whole QTD path. Meanwhile, the proposed statistic can be computed online without storing the entire trajectory of QTD iterates. This substantially reduces the memory requirement and enables efficient statistical inference in distributional reinforcement learning.

Zijie Cheng, Yang Peng, Zhihua Zhang

School of Mathematical Sciences, Peking University · Yau Mathematical Sciences Center, Tsinghua University

Distributional RL Reinforcement Learning Temporal-Difference Learning

Aug 13, 2026cs.CV

A Deep RL based Framework for Targeted White Matter Tractography

Fiber tractography's ability to reconstruct the brain's structural pathways, has made it a crucial component of modern neuroimaging, enabling detailed, non-invasive mapping of structural connectivity and supporting a wide range of neurological research and clinical applications. However, despite its importance, tractography remains a challenging task due to the inherent complexity of white matter structure and its susceptibility to false positives, which can lead to the misrepresentation of critical pathways. To overcome these limitations, in this thesis, we propose a hybrid framework that integrates reinforcement learning with supervised learning for refining RL policies, specifically tailored for tract-specific tractography. Notably, our framework does not rely on ground-truth fibers for training. Moreover, the tract-specific formulation bypasses the need for an explicit segmentation process, simplifying the overall pipeline. Our work includes two main contributions, each building upon the previous. First, we introduce a hybrid approach that combines reinforcement learning with supervised learning (specifically, GPT-based policy learning) to refine policies in a tract-specific context. Second, we propose a scalable framework for data-driven multi-policy fusion, which leverages the complementary strengths of multiple RL policies to improve tractography performance and robustness. We demonstrate the effectiveness of our framework through extensive validation on benchmark public datasets including TractoInferno, HCP, and ISMRM-2015, highlighting its ability to generalize across data sources and accurately reconstruct brain white matter tracts. We believe that these contributions represent significant advancements in the field of tractography, improving robustness, reliability, and accuracy while reducing dependence on ground-truth annotations.

Ankita Joshi

SCHOOL OF COMPUTING AND ELECTRICAL ENGINEERING, INDIAN INSTITUTE OF TECHNOLOGY MANDI · Indian Institute of Technology Mandi, 175005 - INDIA

Reinforcement Learning Magnetic Resonance Imaging Diffusion MRI Neuroimaging

Aug 13, 2026cs.LG

Revisiting Overestimation Bias Problem of Q-learning: Settling Large Discrete Action Space via Action Intersection

This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods. We find that the large action space increases the randomness in Q-value estimation. The randomness makes two paradigms that drive the major literature on the overestimation problem have their own bottlenecks: the coupling paradigm, i.e., the optimal action and its Q-value are estimated with the same Q-function, always has a positive bias. This is because randomness leads to some actions having abnormally high estimated values than their true values, and the coupling methods prefer these actions. The decoupling paradigm, i.e., the optimal action and its Q-value are estimated with two independent Q-functions, always has a negative bias. This is because randomness increases the estimation gap between the two independent Q-tables for the same action. This paper shows that action intersection can be a simple yet powerful strategy to relieve these bottlenecks. The action intersection strategy enables semi-decoupling via two designs: (1) it allows two Q-functions to share a certain fraction of trajectory data; (2) if a data sample is shared, each Q-function is updated using the coupling paradigm; otherwise, using the decoupling paradigm. Two properties make the action intersection strategy powerful: (1) attaining a large bias range, i.e., varying the data sharing fraction, the estimation bias varies from underestimating to overestimating; (2) fine granularity: the action intersection size can be made arbitrarily finer to enable finer control. We consider two experiment settings, i.e., tabular and deep RL, deep RL experiments show that our method outperforms several SOTA baselines drastically; tabular experiments reveal why our method can achieve superior performance.

Pu Li, Tao Tan, Hong Xie +2

Chongqing Institute of Green and Intelligent Technology, Chongqing, China · University of Science and Technology of China, Hefei, Anhui, China

Reinforcement Learning Deep Q-Learning Q-Learning

Aug 13, 2026cs.LG

Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry

We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards. Players cannot communicate during learning but may agree on a protocol a priori. For Problems A and B we propose \texttt{mQ-learning} and \texttt{mQ-learning-intervals}, achieving

\tilde{O}(\sqrt{H^4 S A_{\text{joint}}\, T})

regret, where

H

is the horizon,

S

the state count,

T = KH

the total steps, and

A_{\text{joint}} = \prod_{i=1}^M |\mathcal{A}_i|

the joint action space across

M

players. For Problem C we give \texttt{mEXC} and \texttt{mEXC-Bellman}, two-phase explore-then-commit algorithms with regret

\tilde{O}(H (S A_{\text{joint}})^{1/3} T^{2/3})

. Against the centralized joint-action benchmark, decentralized learning under information asymmetry matches the single-agent Q-learning rate of \cite{jin2018q} up to logarithmic factors. Because

A_{\text{joint}}

grows exponentially in

M

, the bounds are most meaningful for small

M

or small per-player action sets.

Larissa Xu, King Bi, William Chang

Department of Mathematics University of California, Los Angeles Los Angeles, USA · Department of Computer Science University of California, Los Angeles Los Angeles, USA

Regret Minimization in RL Reinforcement Learning Q-Learning Decentralized MARL Multi-Agent Reinforcement Learning

Aug 12, 2026cs.AI

CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications

Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without target demonstrations. We introduce CoAdapt-GUI, a test-time adaptation (TTA) framework that jointly adapts structured workflow context and policy from the agent's own target-app rollouts and rewards. The workflow context retains transferable procedures, failure modes, and verification rules while excluding app-bound source details. This separation allows reusable workflow knowledge to guide adaptation without transferring source-interface state. For policy adaptation, task-context-matched group-relative optimization updates a LoRA adapter on a frozen vision-language model. Across two unseen-app evaluations, CoAdapt-GUI reaches 45.0% on AndroidWorld-Generalization, compared with 37.5% for the reported Policy-Only TTA baseline, and raises AndroidWorld Plus performance from 38.6% to 52.9%. These results show that transfer-constrained workflow context provides substantial gains and that joint policy adaptation further improves held-out performance.

Linqiang Guo, Li Gu, Zihuan Jiang +8

Peter · Concordia University · Mila – Québec AI Institute +2

Reinforcement Learning RL for GUI Agents Test-Time Adaptation of VLMs GUI Agents Mobile GUI Agents

Aug 11, 2026cs.CV

Language-Structured Relational Q-Learning for Threat-Aware Control in Safety-Critical Driving

Natural-language-based scenario generation offers an intuitive means of describing rare and complex driving interactions, yet it is still uncertain whether training with language-structured data leads to truly adaptive control policies. We propose Language-Structured Relational Q-Learning, instantiated through an Ego-Centric Relational Q-Network (ERQ-Net), which jointly learns inter-vehicle relevance and action values from dynamic traffic graphs. Language descriptions define surrounding-vehicle behaviours during training, while prompts and semantic actor roles are hidden from the policy. ERQ-Net must therefore infer threat relevance solely from observable kinematics and interactions. Across 2,500 safety-critical scenarios, language-structured training improves test success from 49-52% to 55-58% and increases adversary-focused attention from 1.2x to 2.1x, demonstrating emergent threat awareness. However, this representational gain does not consistently translate into adaptive control: trained policies perform similarly to the best constant action, while a portfolio of simple policies solves 76% of scenarios. We formalise this discrepancy as a recognition-control gap and show that reward reweighting and margin shaping do not eliminate the resulting policy collapse. Evaluations of realism, criticality, semantic accuracy, and transfer of state-interface representations to CARLA further highlight both the strengths and the constraints of language-structured relational policy learning in safety-critical driving scenarios.

Aditya Humnabadkar, Huaizhong Zhang, Ardhendu Behera

Department of Computer Sciences, Edge Hill University, United Kingdom

Reinforcement Learning Autonomous Driving Safety Evaluation RL for Autonomous Driving

Aug 11, 2026cs.LG

PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR

Reinforcement learning with verifiable rewards (RLVR) spends most of its compute generating groups of long reasoning trajectories. Recent allocators reduce this cost by assigning budgets to prompts, rollouts, or tokens according to a pointwise notion of difficulty or utility. We identify a statistical mismatch: the unclipped leave-one-out group-relative score gradient is not a sum of independent point contributions, but a second-order U-statistic over pairs of rollouts. Completing one rollout therefore reveals contrast with every other completed rollout, and adaptive endpoint selection changes which pair terms are observable. We introduce PAIR (Pairwise-Aware Inclusion Reweighting), which treats short rollout prefixes as vertices and pair-gradient terms as edges of a contrast graph. A prefix-only predictor estimates correctness and remaining token cost; a convex design chooses positive continuation probabilities under an expected suffix-token budget; and each edge induced by completed vertices is inverse-weighted by its logged joint inclusion probability. Under conditionally independent on-policy rollouts and an unclipped, unstandardized objective, the resulting estimator is design-unbiased for the complete candidate-pair gradient. Across compute-matched RLVR runs on Qwen3-1.7B/4B, PAIR improves average accuracy by +1.2 and +1.4 over the strongest pointwise allocator while using 51% and 52% fewer generated tokens than full-group GRPO. A frozen-population estimator audit confirms that unweighted adaptive selection is biased, whereas pair-inclusion correction recovers the complete-pair target at matched suffix cost.

Pixel Nomand, Elena Voss, Marcus Hale +1

University of Wisconsin–Madison · University of Washington

Inverse Probability Weighting Reinforcement Learning RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards

Aug 11, 2026cs.LG

Contextual Quality-Diversity Evolutionary Reinforcement Learning for HVAC Control in Tropical Commercial Buildings

This paper proposes a contextual quality-diversity evolutionary reinforcement-learning controller, CQD-ERL, for the supervisory control of a tropical, water-cooled chiller plant and its associated air side. Rather than converging to a single scalarised policy, the controller maintains a product archive of specialised policies indexed jointly by a data- driven operating context, a cluster of daily weather and load regime, and a context-invariant behaviour descriptor, filled by a gradient-free evolutionary operator and a soft-actor-critic policy-gradient operator that share one replay buffer. Every action is filtered through a deterministic safety shield before execution. The controller is trained on a two-tier reduced-order environment representing the latent load, cooling-tower approach and humidity constraints of a Singapore commercial building, and is evaluated over a full annual backtest against an ASHRAE Guideline 36 baseline.

Tran Le Vu

Reinforcement Learning Building Energy Management Feedback Control Quality-Diversity Optimization Heating, Ventilation, and Air Conditioning Control

Aug 11, 2026cs.LG

Efficient Hypergradient Descent for Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A natural approach is to formulate IRL as a bilevel optimization problem, in which the inner level corresponds to policy optimization under the learned reward and the outer level measures the discrepancy between the induced policy and expert data. However, this formulation is computationally challenging in practice because the outer update requires a hypergradient involving an inverse-Hessian-vector product for the inner objective. We address this challenge by showing that, at the inner optimum, the Hessian of the inner objective is proportional to the Fisher information matrix of the policy, yielding a structured Fisher-based hypergradient closely related to Natural Hypergradient Descent. To address the resulting scalability bottleneck associated with large Fisher matrices, we approximate the required inverse-Fisher-vector product using a streaming spectral sketch, avoiding explicit construction of the Fisher matrix. We evaluate our approach against a first-order stochastic bilevel baseline across discrete- and continuous-control environments. The results demonstrate competitive policy performance and strong reward-ranking quality, while Fisher sketching reduces curvature-storage complexity and can improve computational efficiency relative to an explicit Fisher solver.

Nikita Sevriukov, Anna Barabanova, Uliana Gagarina +4

HSE University Moscow, Russia

Reinforcement Learning Gradient Descent Natural Gradient Methods Bilevel Optimization

Aug 11, 2026cs.LG

IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning

Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficient decision making. Numerous methods have been developed to improve dynamics prediction and policy optimization for MBRL through uncertainty estimation, model regularization, and conservative value learning. However, these methods typically treat the transition model and critic as monolithic predictors, overlooking the policy-induced data bias. Consequently, action can become entangled with environmental evolution, while uneven action coverage may distort the counterfactual value estimates used for policy improvement. To address this, we propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR). IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization. Its latent and state-aligned components are identifiable up to an invertible within-block transformation and pointwise, respectively. For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional. TR augments the critic with an action-density-scaled residual correction and optimizes a targeted loss, yielding doubly robust policy-gradient estimation when either the critic or the replay action density is consistently specified. Extensive experiments on five MuJoCo tasks show that IADD-TR achieves competitive returns with improved sample efficiency.

Zefeng Liang, Jie Qiao, Ruichu Cai +2

School of Computer Science, Guangdong University of Technology, Guangzhou, China · College of Science, Shantou University, Shantou, China

Reinforcement Learning Robust RL Causal RL Sample-Efficient RL Model-Based RL

Aug 11, 2026cs.AI

Reinforcement Learning-Based Laser Cutting Machine Parameter Optimization

Achieving high accuracy in laser-based cutting of optical films requires careful tuning of parameters such as focal length and laser power beam, adjusted according to the specific properties of each film type. Trial-and-error based traditional methods are used to find the most suitable cutting parameters for various films, but they are slow and inaccurate. To address this issue, this paper presents the Reinforcement Learning for Laser Cutting (RL

^{2}

C) algorithm, which uses Q-learning with an epsilon-greedy policy to dynamically optimize cutting parameters, significantly reducing taper size and film wastage. Additionally, RL

^{2}

C incorporates a dynamic environment space adaptability mechanism to allow it to adapt to new states encountered during the learning process over multiple batches of experiments. Experimental results demonstrate that RL

^{2}

C requires fewer steps and less time to find optimal cutting parameters compared to various RL-based optimization methods. Specifically, RL

^{2}

C reduces the number of optimization steps by up to 12.5% and processing time by up to 81.8% compared to existing methods. This study demonstrates the potential of RL in industrial laser-cutting processes by improving cut quality, reducing time and film wastage, and minimizing manual interventions.

Khanh Quan Pham, Majid Kundroo, Geunwoo Ban +2

School of Information and Communication Engineering, Chungbuk National University, Cheongju, 28644, Korea. · NPS CO., LTD., Cheongju, 28371, Korea.

Manufacturing Reinforcement Learning

Aug 11, 2026cs.LG

Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning

Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly reusing an offline-trained critic can hinder online fine-tuning: as the policy and data distribution change rapidly, value estimates inherited from offline training may become misaligned with the online environment, leading to inaccurate policy improvement and inefficient exploration. To address this problem, we introduce Critic-Free Pretraining: an efficient paradigm that completely abandons the approach of offline critic training, allowing a freshly initialized critic to adapt without inheriting biased estimates. CFP is compatible with various mainstream O2O algorithms and consistently matches or improves upon conventional O2O algorithms across a diverse set of tasks, with particularly pronounced gains on several challenging tasks.

Daoyi Li, Yixian Zhang, Wenbo Ding +2

Tsinghua University

Reinforcement Learning Critic-Free RL RL Fine-Tuning Policy Learning Offline-To-Online RL

Aug 11, 2026cs.LG

TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling

Reinforcement learning (RL) for large language models is moving toward multi-turn agentic workloads, where rollout tasks repeatedly pause for external environments, resume with growing contexts, and finish at highly variable times. In this setting, RL training goodput, measured by training throughput, matters more than raw GPU occupancy: GPU waiting and repeated prefill recomputation are pure overhead. We present TideRL, a readiness-aware elastic RL system with Continuous Task Batching, Resource-Aware Ref-Actor Pipelining, and Elastic Resource Scaling. CTB preserves useful rollout state,

\textrm{RA}^2\textrm{P}

selects between decoupled streaming and colocated aggregation from the ready backlog and arrival interval, and ERS moves ranks between rollout and training using the same readiness signals. Across text-only and multi-modal agentic workloads, TideRL improves RL training goodput by up to 5.6

\times

over synchronous baselines and over 33% over asynchronous baselines, while reaching similar task performance. It also improves KV cache hit rate by 1.58

\times

, reduces per-step training time by up to 44.3%, and cuts total waiting time by up to 77.6%.

Yanyu Ren, Xizheng Wang, Xiao Liu +8

Tsinghua University · Zhongguancun Laboratory

Agentic RL Asynchronous RL Reinforcement Learning RL for LLM Agents