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 27, 2026cs.LG

Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach

We study the transfer of rewards learned using inverse reinforcement learning from expert demonstrations in one environment to reinforcement learning in a new, different environment. This arises naturally when demonstrations are collected in a controlled environment. We formulate the problem as a joint system of Bellman equations across the source and target environments and develop minimax estimators for the target soft-

q

-function. Whereas a sequential solution approach first estimates the source reward and then plugs it into the target control problem, a coupled approach solves the source and target system of equations jointly. We show that, in contrast to the sequential approach, the coupled approach removes the first-order influence of source Bellman residual error. We characterize the local behavior of each approach, develop finite-sample soft-

q

-function error bounds, and prove regret guarantees for the resulting soft-control policy. An empirical investigation using a sepsis simulator validates the theoretical comparison.

Guang-Yuan Hao, Lars van der Laan, Aurélien Bibaut +1

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

Reinforcement Learning Minimax Estimation

May 26, 2026cs.LG

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO, however, whose group-relative advantage naturally concentrates learning on a sweet spot of intermediate-difficulty questions, SDPO's KL-based advantage lacks an implicit notion of difficulty awareness. We analyze this gap through the lens of GRPO's advantage normalization. Extending the learnability framework to normalized rewards, we show that normalization absorbs the variance term

p(1-p)

, equalizing leading-order learnability across questions and leaving

\sqrt{p(1-p)}

as the sole residual scaling factor in the per-question gradient. This analysis yields a simple prescription: weight each question's SDPO loss by

[\hat{p}(1-\hat{p})]^{1/2}

, resulting in SC-SDPO, a scale-consistent variant of SDPO. The proposed weights are obtained as a zero-cost byproduct of on-policy rollouts with batch-adaptive normalization, inducing an implicit curriculum that dynamically tracks the model's evolving competence. Experiments on scientific reasoning and tool-use benchmarks demonstrate that SC-SDPO consistently improves over SDPO, yielding gains of +3.2/+4.3 (mean@16/maj@16) on Qwen3-8B and +1.8/+3.0 on OLMo-3-7B, while preserving stable training dynamics throughout optimization.

Zehao Liu, Yuanpu Cao, Jinghui Chen +1

College of Information Sciences and Technology Pennsylvania State University

Reinforcement Learning On-Policy Self-Distillation RL for Language Model Reasoning Curriculum RL

May 26, 2026cs.LG

Bayesian Deployment Approval for Learned Landing Controllers under Finite Rollout Validation

Reinforcement learning and data-driven autonomous controllers are commonly evaluated using cumulative reward and empirical success frequency under finite simulation trajectories. However, such empirical metrics do not necessarily provide sufficient statistical evidence regarding deployment readiness under uncertainty. This work develops a Bayesian approval framework for learned autonomous landing controllers under finite rollout evidence. A probabilistic landing capability formulation is introduced based on touchdown safety satisfaction under uncertain operating conditions, while Bayesian posterior inference is used to quantify uncertainty regarding the true deployment capability of learned policies. Posterior approval probability and posterior deployment risk are further introduced for deployment-oriented evaluation, together with a sequential validation framework supporting approve/reject/continue decisions during progressive rollout testing. Simulation experiments using PPO and SAC controllers demonstrate that empirical success and reward optimization may produce overconfident deployment interpretation under limited validation evidence, whereas posterior approval inference provides a more uncertainty-calibrated assessment of deployment readiness. The proposed framework provides a practical statistical connection between conventional reinforcement-learning evaluation and deployment-oriented validation under uncertainty and may be generalized to broader classes of learned autonomous systems.

Fei Jiang, Lei Yang

Independent Researcher, Seattle, WA, USA.

RL Control Reinforcement Learning

May 26, 2026cs.LG

Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments, they often suffer from performance degradation or safety violations because of the inevitable Sim2Real gap. Existing zero-shot approaches, such as robust safe RL and domain randomization, mitigate this issue but typically at the cost of degraded performance or residual safety risks when experiencing unmodeled system dynamics. To address these limitations, we propose a novel reinforcement learning framework that enables safe and efficient policy transfer via probabilistic latent embeddings and dynamic policy adaptation. We consider a family of Constrained Markov Decision Processes (CMDPs) under different environment contexts. By leveraging latent context variable in meta-RL, the proposed framework infers the latent representation of the environment from simulated experiences. Furthermore, it incorporates a distributional RL formulation, which allows risk levels of the deployed policy to be adjusted dynamically, based on the estimation accuracy of the latent context variable. This strategy promotes safety at the early deployment stage and improves efficiency through fast policy adaptation under the Sim2Real gap.

Gengyue Han, Yiheng Feng

Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette, USA · Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, USA

Reinforcement Learning Sim-to-Real Transfer Constrained RL Meta-Reinforcement Learning Safe RL

May 26, 2026stat.ML

Accelerating Reinforcement Learning Training Using Simulation Surrogate Models

High-fidelity simulation models are widely used to analyze complex stochastic systems, but their high computational cost motivates the development of cheaper surrogate models that approximate the simulation model's input-output relationship. In parallel, reinforcement learning (RL) has emerged as a powerful framework for making online decisions in stochastic environments, with increasing attention being given to the use of simulation models as training environments for RL models. We investigate a class of surrogate models suitable for accelerating RL training in settings where the reward structure, model parameters, or system dynamics change over time and explore their interactions with simulation models and RL models. Through numerical experiments on a stochastic service system modeled via discrete-event simulation, we demonstrate that leveraging surrogate models can substantially accelerate RL training and re-training.

Mohammadmahdi Ghasemloo, David J. Eckman, Yaxian Li

Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, USA · Intuit AI, Mountain View, CA, USA

Surrogate Modeling Reinforcement Learning Model-Based RL

May 26, 2026cs.LG

Trust Region Q Adjoint Matching

Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-learning with Adjoint Matching (QAM) addressed this by recasting policy improvement as a stochastic optimal control (SOC) problem guided by a learned critic. However, QAM inherits a fundamental fragility of critic-guided improvement, since small critic errors can be exponentially amplified and often lead to performance collapse. This paper introduces Trust Region Q Adjoint Matching (TRQAM), a stable off-policy fine-tuning algorithm that adaptively controls the path-space KL between the fine-tuned and pretrained policies through projected dual descent. Specifically, we adapt a trust-region parameter

λ

inside the sampling process of the flow policy and prove that

λ

exactly weights the path-space KL in the SOC objective. As a result, our method can tightly control the deviation from the pretrained policy within a prescribed KL budget, achieving stable off-policy RL. Through experiments on 50 OGBench tasks, TRQAM consistently outperforms prior methods in both offline RL and offline-to-online RL. In particular, TRQAM achieves an overall success rate of 68% in offline RL, substantially improving over the strongest baseline at 46%.

Yonghoon Dong, Kyungmin Lee, Changyeon Kim +2

KAIST AI · Seoul National University · RLWRLD

Reinforcement Learning KL-Regularized RL Offline RL Trust Region Policy Optimization RL Fine-Tuning Offline-To-Online RL

May 26, 2026cs.LG

SQARL: A Size-Agnostic Reinforcement Learning approach for Circuit Allocation in Distributed Quantum Architectures

The scaling of quantum processors is currently limited by technical challenges such as decoherence and cross-talk. As the number of qubits grows, interference increases the computational noise. Distributed quantum computing addresses these limitations by interconnecting smaller, easier-to-handle quantum processors (cores), but it introduces the challenge of minimizing slow, error-prone inter-core communication. The task of distributing quantum circuits across cores while minimizing communication costs is known as the Qubit Allocation problem. This work focuses on developing a deep learning approach to this problem, emphasizing flexibility to quantum hardware topology and improving state-of-the-art performance. Heuristic and non-learning algorithms, such as the Hungarian Qubit Allocation (HQA), currently represent the state of the art. Reinforcement Learning (RL) approaches leverage learned allocation policies but often lack flexibility, requiring retraining when hardware configurations change, and they fall short of the solution quality achieved by non-learning methods. However, learning mechanisms could outperform human-crafted heuristics. To overcome these limitations, this work proposes a flexible, transformer-based architecture that can handle arbitrary numbers of qubits and cores without retraining. Results show that the trained policy consistently outperforms the previous RL state of the art and narrows the gap between RL and HQA for the most common circuits. It achieves a 33% reduction in allocation cost relative to the HQA for the Cuccaro Adder and 25% on average for random circuits. These findings show that learning-based approaches can effectively match the performance of hand-crafted heuristics, a crucial step towards their application in real-world scenarios.

Víctor Carballo, Júlia López-Closa, Mario Martin

Computer Science Department, Universitat Polit`ecnica de Catalunya - BarcelonaTech (UPC) · High Performance Artificial Intelligence group, Barcelona Supercomputing Center.

Reinforcement Learning

May 26, 2026cs.AI

Darwin Mobile Agent: A Roadmap for Self-Evolution

The goal of artificial intelligence is to create agents capable of general, adaptive behaviour in open-ended environments. Guided by the "Bitter Lesson", we argue that the most effective path toward this goal is to systematically remove human priors and allow intelligence to naturally emerge through interaction with a "Big World" that is orders of magnitude more complex than the agent itself. We propose the mobile Graphical User Interface (GUI) as a practical proxy for such a world and introduce Darwin Mobile Agent, an open-source infrastructure designed as a foundation for autonomous reinforcement learning in this domain. This framework addresses the data-collection bottleneck in real-world mobile interactions by using an asynchronous agent-environment loop across parallel cloud-phone instances. We further propose a conceptual roadmap to systematically remove human priors from three fundamental pillars of a self-evolving agent: task curricula, outcome verification, and memory management. We validate that the Darwin infrastructure provides the stability and scalability required for the first stage of this roadmap: policy optimisation in the GUI domain. This work establishes the practical and theoretical foundation necessary to move toward truly autonomous, self-evolving GUI agents.

Daniel Beechey, Derek Yuen, Jianheng Liu +5

1Huawei Noah’s Ark Lab · University College London

Reinforcement Learning RL for GUI Agents GUI Agents Mobile GUI Agents Distributed RL Self-Evolving Agents

May 26, 2026cs.LG

Probabilistic Recurrent Intention Switching Model

Inverse reinforcement learning (IRL) recovers reward functions from observed behavior, yet traditional methods assume a single stationary reward that cannot capture goal switching within an episode. Recent multi-intention IRL methods address this by segmenting trajectories, but model intention transitions as either a memoryless Markov chain or via manual state augmentation with a fixed history window. We propose the Probabilistic Recurrent Intention Switching Model (PRISM), which replaces both mechanisms with a lightweight recurrent network that maps observation history to a per-step intention distribution. We prove that the resulting EM objective decomposes exactly into independent per-intention reward subproblems, each solvable in closed form, yielding an

\mathcal{O}(nK)

E-step with no variational approximation. We evaluate PRISM on a non-Markovian gridworld, a mouse labyrinth, and BridgeData~V2 robotic manipulation, the first large-scale robotic application of multi-intention IRL. Across all settings PRISM achieves the highest held-out log-likelihood while recovering nameable, temporally coherent intentions from unlabeled demonstrations, suggesting that discrete goal switching is present in both biological and artificial agents.

Wenyuan Sheng, Hao Zhu, Joschka Boedecker

Department of Computer Science, University of Freiburg · IMBIT//BrainLinks-BrainTools

Reinforcement Learning

May 26, 2026cs.CV

REVERSE: Reinforcing Evidence Verification and Search for Agentic Image geo-localization

Image geo-localization aims to determine where a photograph was taken, a task that often requires more than recognizing visible landmarks. Human experts typically solve it through an iterative workflow: they inspect informative regions, form location hypotheses, seek external evidence, and revise their judgments as new clues appear. Existing methods only partially capture this process: direct prediction methods bypass evidence acquisition altogether, while retrieval-augmented methods introduce external evidence but usually provide limited supervision on the intermediate decisions of where to search, how to query, and how to filter noisy results. We present REVERSE, a framework that reinforces the interplay between evidence search and verification to enable multi-turn agentic reasoning. REVERSE teaches three intermediate decisions: where to look, what to query, and what evidence to trust. To support this, we construct tool-grounded trajectories with annotated region selections, search observations, and geo-informative evidence labels, and introduce process rewards for visual grounding, query utility, and evidence discrimination. An offline search cache makes retrieval observations stable and reusable during reinforcement learning, enabling dense supervision over noisy search results. With a 4B model, REVERSE outperforms strong retrieval-augmented baselines and rivals substantially larger models on Im2GPS3k and YFCC4k. Code is available at https://github.com/yonglleee/REVERSE.

Yong Li, Furong Jia, Dacheng Yin +4

Peking University · The Hong Kong University of Science and Technology · WeChat Vision, Tencent Inc

Retrieval-Augmented Generation Reinforcement Learning Geospatial Reasoning

May 26, 2026cs.LG

Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts

In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which limits their performance under real-world distribution shifts. In this paper, we aim to develop a generalization-oriented model that partitions the policy network into multiple modules and adaptively recombines modules to form specific policies during inference. Specifically, we propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cross-distribution generalization. Our contributions are threefold: (1) We introduce a Residual Refined Expert (R2E) architecture that enhance expert expressiveness via residual refinement; (2) We design an instance-level gating mechanism that learns distribution-aware instance representations and routes inputs to suitable modules; (3) We propose a mixed-distribution training mechanism equipped with Dynamic Weight Adaption (DWA), which dynamically reweights training data from different distributions to emphasize more informative ones. Extensive experiments show that R2E-IG achieves competitive performance against state-of-the-art baselines on both in-distribution and out-of-distribution instances across synthetic and benchmark datasets. Moreover, R2E-IG is generic and can be easily integrated into existing DRL-based methods to further improve performance.

Changhao Miao, Yuntian Zhang, Tongyu Wu +2

State Key Laboratory of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing 100081, China · Department of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, Rome, 00185, Italy · School of AI, Beijing Institute of Technology, Beijing 100081, China

Reinforcement Learning Adaptive Model Routing Vehicle Routing Cross-Domain Generalization Mixture-of-Experts Models RL for Combinatorial Optimization

May 26, 2026cs.CV

MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentation

Volumetric Reasoning Segmentation (VRS) aims to segment a target region in a 3D medical scan from a free-form clinical query, where the referent is often implicit and requires both medical knowledge and volume-grounded reasoning. Existing methods typically rely on specialized segmentation tokens to connect language with mask decoding, but this coupling collapses the decision process into opaque latent representations, limiting interpretability and generalization to diverse narrative expressions. In this paper, we present MedVol-R1, a reinforcement learning-based framework for VRS that explicitly decouples evidence grounding from volumetric delineation: the LVLM grounds clinical reasoning to a verifiable 2D evidence anchor (key axial slice and 2D bounding boxes), which is then propagated into a coherent 3D mask by a frozen MedSAM2 module. We train MedVol-R1 with cold-start supervised fine-tuning followed by GRPO, guided by a multi-component reward that encourages informative evidence selection, accurate 2D spatial grounding, and cross-slice volumetric coherence, without requiring costly chain-of-thought annotations. Experiments on CT-ORG, AbdomenCT-1K, and KiTS23 from the M3D-Seg benchmark demonstrate that MedVol-R1 consistently outperforms strong baselines and achieves state-of-the-art performance, with reinforcement learning providing clear gains over pure supervised fine-tuning.

Zichun Wang, Hairong Shi, Bingzheng Wei +2

School of Biological Science and Medical Engineering, Beihang University, Beijing, China · Center for Information and Computer Science, School of Science for Open and Environmental Systems, Graduate School of Science and Technology, Keio University, 2026 Kanagawa, Japan · Bytedance Inc., China +1

Image Segmentation Reinforcement Learning Promptable Image Segmentation Medical VLMs 3D Medical Image Segmentation Medical Image Grounding

May 26, 2026eess.SP

Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks

Reinforcement Learning (RL) has long been a powerful solution to various problems in communication networks. However, traditional RL models still face with several limitations. Not only do they rely on large numbers of interactions with the environment, but they are also limited in terms of modeling long-term relationships and tackling partial observability. In recent years, the Transformer model has demonstrated the ability to enhance RL models, allowing them to overcome these issues. Particularly, the self-attention mechanism within the Transformer enables efficient modeling of long-range dependencies and global correlations, as well as accelerates training processes and handles heterogeneous data modalities. In this paper, we present a comprehensive survey of Transformer-based RL algorithms and their applications in communication networks. Specifically, the paper provides the mathematical background of RL and Transformer architectures, along with insights into key issues such as resource allocation, computation offloading, routing, and trajectory control, and network security. We conclude the paper by discussing challenges, open issues, and notable future research directions, including Transformer-enhanced DRL algorithms for semantic communication and network optimization.

Nguyen Cong Luong, Shaohan Feng, Nguyen Duc Hai +10

Faculty of Computer Science, Phenikaa University, Hanoi 12116, Vietnam · School of Information and Electronic Engineering (Sussex Artificial Intelligence Institute), Zhejiang Gongshang University, Hangzhou 310018, China · Faculty of Artificial Intelligence and Data Science, Phenikaa University, Duong Noi, Hanoi 12116, Vietnam +4

Reinforcement Learning Transformer-Based RL Wireless Communications

May 26, 2026cs.LG

Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training

Reinforcement learning (RL) is the dominant paradigm for post-training large language models. However, in the online, on-policy setting, rollout generation dominates the computational cost of training. Group-based policy optimization methods compute advantages from multiple rollouts per prompt, yet they indiscriminately allocate budget to prompts with collapsed reward distributions, wasting expensive rollouts on negligible learning signals. We demonstrate that group-based updates are most effective in regimes of high reward variance. Since the policy evolves throughout training, prompt informativeness must be estimated online rather than precomputed, but exhaustively evaluating every prompt is computationally prohibitive. We introduce Pilot-Commit, a budget-aware rollout allocation framework for group-based RL post-training. Pilot-Commit decouples prompt evaluation from exploitation: a pilot stage estimates per-prompt informativeness using a fraction of the budget, and the remaining rollouts are allocated to high-leverage prompts while low-signal prompts are skipped. Across multiple math reasoning benchmarks and model scales from 1.5B to 14B parameters, Pilot-Commit matches baseline accuracy with significantly lower sampling costs, reaching target accuracy up to

1.9\times

faster than GRPO and

4.0\times

faster than DAPO in cumulative rollouts.

Woojeong Kim, Ziyi Yang, Jing Nathan Yan +1

Databricks · Cornell University

Reinforcement Learning RL for Language Model Reasoning Group Relative Policy Optimization RL Post-Training

May 26, 2026cs.RO

Heterogeneous AAV Logistics Task Allocation: A Reinforcement Learning Enhanced Overlapping Coalition Formation Game Approach

In dynamic urban logistics, the stochastic emergence of time-sensitive tasks poses a significant optimality challenge for heterogeneous AAVs logistics task allocation. To address this problem, a reinforcement learning enhanced overlapping coalition formation game approach is proposed. A dynamic task allocation model is established, where global optimality is mathematically quantified by a generalized logistics cost coupling service quality and resource consumption. To deal with the time-varying task sets induced by stochastic order arrivals, a transformer-based soft actor-critic network is designed. By leveraging multi-head self-attention to encode variable-length logistics states and capture task-wise spatiotemporal dependencies, the learned policy adaptively guides coalition updates, replacing heuristic rules in the overlapping coalition formation game. On this basis, heterogeneous AAVs can form more efficient overlapping coalitions for dynamic logistics tasks. The resulting coalition formation process is proven to constitute an exact potential game, which guarantees convergence to a Nash-stable equilibrium within a finite number of iterations. Numerical simulations demonstrate that the proposed algorithm effectively improves the optimality of task allocation under the generalized logistics cost criterion. In a scenario with 32 AAVs and 80 tasks, our algorithm achieves a 39.76% cost reduction compared with the heuristic OCF baseline. Indoor flight experiments further validate its practicality.

Yuze Zhou, Jingliang Sun, Junzhi Li +3

Beijing Institute of Technology, Beijing 100081, China · Key Laboratory of Dynamics and Control of Flight Vehicle, Ministry of Education, Beijing 100081, China · Beijing Institute of Technology Chongqing Innovation Center, Chongqing, 401121, China +1

Reinforcement Learning Transformer-Based RL Multi-Robot Task Allocation

May 26, 2026cs.AI

From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator

A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline logs (Static Context RL) or using a prompt-based simulator (Interactive RL). In this work, we theoretically show that both paradigms are fundamentally limited by context distribution shift--a mismatch between dialogue histories observed during training and those encountered in real conversations. This shift compounds quadratically over turns and severely degrades dialogue quality. Specifically, we attribute this shift to two distinct sources: (i) policy-induced shift, arising from training on static histories rather than self-generated trajectories; and (ii) simulator-induced shift, stemming from discrepancies between simulated and real human behaviors. To address these challenges, we propose Calibrated Interactive RL, a unified framework that couples interactive RL with simulator alignment. By aligning the simulator with human interaction patterns, our approach reduces the sim-to-real gap and mitigates compounding distribution shifts. Experiments across multiple dialogue tasks confirm our theoretical analysis: (i) Interactive RL significantly outperforms the Static Context baseline by mitigating policy distribution shift; and (ii) calibrating simulators with our alignment method further bridges the sim-to-real gap, yielding state-of-the-art downstream performance.

Xiaohua Wang, Jiakang Yuan, Zisu Huang +5

Fudan University

RL for Language Models Reinforcement Learning Human Behavior Simulation Conversational Agents User Simulation

May 25, 2026cs.LG

Balancing Plasticity and Stability with Fast and Slow Successor Features

A hallmark of intelligence is the ability to adapt in non-stationary environments, yet deep Reinforcement Learning (RL) agents often struggle in such settings. Prior studies introduce non-stationarity through abrupt shifts in features or dynamics, whereas real-world environments often evolve gradually through continual drift. This distinction has important implications for the "stability-plasticity dilemma" in RL, as abrupt task changes may demand more plasticity than naturalistic settings. To address this, we modify existing 3D Miniworld and MuJoCo environments to incorporate naturalistic, continual non-stationarity, and use them to examine how stability and adaptation affect performance under continuous environmental change. We find that methods favoring stability, such as synaptic consolidation, outperform approaches focused on plasticity, such as parameters resetting. Motivated by this result, and prior evidence that Successor Features (SFs) reduce interference, we investigate whether SFs are better consolidation targets than Q-values. Across both environments, applying neuro-inspired synaptic consolidation to SFs yields superior performance on continually changing settings. Moreover, consolidation is most effective when SFs are stabilized across multiple timescales, which capture complementary aspects of gradual environmental change. Together, these results suggest that stability is more critical in continual learning when changes are gradual, and that multi-timescale consolidation of predictive representations is an effective approach.

Raymond Chua, Doina Precup, Blake Richards

School of Computer Science, McGill University, Montr´eal, Canada · Mila - Quebec Artificial Intelligence Institute, Montr´eal, QC, Canada · CIFAR Learning in Machines and Brains +3

Stability-Plasticity Dilemma Non-Stationary RL Reinforcement Learning Sequential Decision Making Memory Consolidation Continual RL

May 25, 2026cs.CL

Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Use

We test the standard RLVR tool-use recipe -- GRPO on Qwen2.5-7B-Instruct -- on a deliberately minimal knowledge-graph tool API: four Freebase navigation verbs over Complex WebQuestions. Under a self-verifiable retrieval reward, the policy's tool-grounded answer rate climbs from

3.8\%

to

9.6\%

over 250 steps, then collapses to

0\%

within a single 50-step window -- a \emph{peak-then-collapse} pattern replicated across four seeds. Across seven reward designs, we find four recurring failure modes: adding denser or more targeted proxy rewards shifts the failure mode rather than eliminating it. We argue that a key difference from Python interpreters, web search, and JSON APIs is interface feedback: their failures often leak natural-language signal the model saw in pretraining. A Python traceback names the failing line; an empty Freebase result \texttt{[]} does not. Stripping away that surface exposes a degradation regime that same-family reward redesigns do not fix. A direct oracle ablation rules out relation selection: injecting gold relations at every retrieval call lifts exact-match accuracy by only

+0.20

~pp, and

95.4\%

of retrieval-dependent errors are retrieval-composition failures rather than answer-extraction failures. As a mitigation, one-iteration self-distillation reaches

40.0\%

EM at 7B and is capacity-invariant: doubling capacity to 14B improves EM by only

0.25

~pp, and initialization barely matters -- the ceiling appears interface-bound within the 7B--14B range tested.

Tianda Sun, Dimitar Kazakov

University of York · Department of Computer Science · Heslington, York +1

Tool-Use Evaluation Reinforcement Learning Knowledge Graph Question Answering RL for Tool Use

May 25, 2026cs.LG

Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning

Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intrinsically low-dimensional. In this work, we present a simple yet effective representation-level prior that inserts a fixed orthonormal projection to constrain encoder features to a low-dimensional subspace, requiring no auxiliary objectives, pretraining, or changes to the underlying RL algorithm. Under a linear realizability assumption, we prove that when the bottleneck dimension exceeds the intrinsic rank of the optimal value function in feature space, the bottleneck preserves expressivity and leaves the induced gradient dynamics unchanged up to an equivalent low-dimensional parameterization. Empirically, we find that across both single and multi-task benchmarks, baseline performance is either matched or improved once the bottleneck dimension exceeds a small task-dependent threshold; in many cases, value representations can be compressed to extremely low dimensions without loss, and the minimal sufficient dimension depends far more on environment complexity than encoder width. In addition, we analyze representation geometry and find that orthogonal bottlenecks stabilize feature norms and are associated with higher effective rank. Together, these results support a representation-space interpretation of the manifold hypothesis in reinforcement learning and position orthogonal bottlenecks as a lightweight, architecture-agnostic mechanism for shaping RL representations.

Aleksandar Todorov, Matthia Sabatelli

University of Groningen, Groningen, The Netherlands

Representation Learning Reinforcement Learning Information Bottleneck Orthogonal Representation Learning Representation Learning for RL State Representation Learning

May 25, 2026cs.LG

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards

Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labels for reward computation, the acquisition of which is often prohibitively expensive in real-world scenarios. While unsupervised RLVR paradigms attempt to circumvent this by training on pseudo-labels, they are notoriously susceptible to training collapse. Moreover, different samples often exhibit varying annotation values. In this paper, we propose Reinforcement Learning with Active Verifiable Rewards (RLAVR), which actively acquires ground-truth labels for a small set of selected samples and integrates them with pseudo-labels, thereby stabilizing training dynamics and improving performance under limited annotation budgets. To identify valuable samples, we propose the Corrective Advantage Gap (CAG) metric and analyze the sample-level supervision value. Building on this, we introduce Correction-Aware Reliability Estimation for RLAVR (CARE), which translates the oracle CAG criterion into a practical pre-query acquisition policy to substantially improve training stability. Extensive experiments across diverse domains, model families, and model scales demonstrate the effectiveness and generality of our approach. Our code is available at https://github.com/Lumina04/CARE.

Li Wang, Xiaodong Lu, Xiaohan Wang +5

Meituan · Beihang University · Nanyang Technological University

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

May 25, 2026cs.LG

Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning

Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-conditioned value function in long-horizon tasks remains challenging. In this paper, we identify erroneous generalization in goal-conditioned value functions as a fundamental bottleneck, and demonstrate that appropriate inductive bias in the value function is crucial for addressing the bottleneck. Building on these findings, we propose Latent-Aligned Value Learning (LAVL), an offline GCRL algorithm that integrates latent-representation-based value generalization with hierarchical planning in a unified framework. Extensive experiments on OGBench demonstrate that LAVL consistently outperforms existing offline GCRL methods, achieving the highest performance on 20 out of 22 datasets. Notably, LAVL exhibits strong performance in long-horizon tasks and trajectory stitching datasets, where prior methods suffer significant performance degradation. Our code is available at https://github.com/oh-lab/LAVL.git.

Hyungkyu Kang, Byeongchan Kim, Min-hwan Oh

Seoul National University, Seoul, South Korea.

Reinforcement Learning Offline RL Representation Learning for RL Goal-Conditioned RL

May 25, 2026cs.AI

Learning to Search and Searching to Learn for Generalization in Planning

Combinatorial generalization remains a central challenge in Deep Reinforcement Learning (DRL). Classical planning provides a simple yet challenging setting to study this problem through explicit relational descriptions, without requiring learning from perception. In sparse-reward domains, standard RL exploration via real-time search is ineffective, and learning-based planning methods often rely on expert demonstrations, hindsight relabeling, or random walks from the goal state. In contrast, planners rely on best-first search methods such as

\mathrm{A}^\star

to solve problems from scratch. We propose a self-improving

\mathrm{WA}^\star

learning framework in combination with a value heuristic represented by a Relational Graph Neural Network: the heuristic guides search, and the resulting search data updates the heuristic via

Q

-learning. This loop yields heuristics that can function as general policies and solve new instances even without search, where DRL otherwise fails, as we show on puzzles such as Sokoban, PushWorld, The Witness, and the 2023 International Planning Competition benchmarks. Notably, we demonstrate strong zero-shot generalization: For example, heuristics trained on Blocksworld instances with fewer than 30 blocks successfully solve instances with 488 blocks without search.

Michael Aichmüller, Yannik Hesse, Hector Geffner

Department of Machine Learning and Reasoning, RWTH Aachen University, Aachen, Germany.

Reinforcement Learning Generalization in RL

May 25, 2026cs.CL

Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models

Post-training via Reinforcement Learning (RL) has enabled Large Reasoning Models (LRMs) to achieve strong performance in individual domain. However, real-world applications increasingly require general-purpose reasoners rendering strong performance across diverse domains. Mixed-domain post-training aims to achieve this goal by jointly training with mixed domain data, but this often induces capability compromise and degradation among different domains. Existing methods attribute this performance degradation to harmful cross-domain interactions and propose various strategies to mitigate them, but these strategies may also impede beneficial knowledge sharing across domains and in turn fail to match or surpass single-domain performance. To address this problem, we propose \textbf{M}ulti-domain \textbf{C}ontrastive \textbf{P}olicy \textbf{O}ptimization (MCPO), which uses contrastive learning to utilize both positive and negative cross-domain interactions for knowledge sharing and competition. Specifically, we partition each rollout generated by LRMs according to its underlying reasoning structures and use reasoning segments to capture these structures. We thus formulate positive and negative pairs of reasoning segments as mutually augmented examples, which provide supportive and competing signals for knowledge sharing. Subsequently, we design complementary contrastive objectives for cross-domain knowledge sharing and intra-domain knowledge consolidation, targeting compatibility across domains and discriminability within each domain to form a harmonious reasoning space. Experimental results across a broad range of domains show that MCPO alleviates performance degradation caused by mixed-domain training and outperforms single-domain training in most cases.

Zongji Yu, Wenshui Luo, Yiliu Sun +5

Shanghai Jiao Tong University · Shanghai AI Laboratory · Shandong University

Reinforcement Learning RL for Language Model Reasoning Cross-Domain Transfer Learning Multi-Task RL Contrastive RL Large Reasoning Models

May 25, 2026cs.RO

Prior Policy Guided Dual-Agent Coordinated Manipulation Planning of Spacecraft-Manipulator System

The strong dynamic coupling between the manipulator and the base poses a significant challenge to maintaining spacecraft attitude stability, potentially compromising mission safety. In this paper, we propose a Dual-Agent Coordinated Manipulation Planning (DACMP) framework that simultaneously achieves high-precision end-effector pose reaching for a 6-DoF space manipulator and attitude stabilization of the base spacecraft. To enhance learning efficiency, we present a prior policy-guided Deep Reinforcement Learning algorithm incorporating the Timestep-level Expert Switching Guidance (TESG) mechanism, thereby promoting global convergence and improving task success rates. Extensive experiments demonstrate that DACMP significantly outperforms baseline DRL algorithms in terms of task success rate and control precision. Furthermore, the robustness of DACMP is validated under various challenging scenarios, including system constraints, environmental disturbances, and perception uncertainties. The code and simulation configurations are available on GitHub: https://github.com/HIT-YuhuiHu/DACMP.

Yuhui Hu, Dong Zhou, Kaihong Ouyang +3

School of Astronautics, Harbin Institute of Technology, Harbin, 150001, China · School of Automation, Chongqing University, Chongqing, 400044, China · School of Information Science and Engineering, Lanzhou University, Lanzhou, 730000, China

Robotic Control Reinforcement Learning Multi-Agent Control Robotic Manipulation

May 24, 2026cs.LG

Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning

Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts, pretraining-only safe ICRL can give poor reward-safety tradeoffs because the remaining budget affects behavior only through frozen policy conditioning, not an explicit action-level check against predicted future cost. We propose a latent Q-Barrier shield that learns a context representation, latent dynamics, and an ensemble cost critic before deployment. Without parameter updates, the shield infers context from history and filters or softly reweights candidate actions using the remaining budget and predicted future cost. We prove a conditional, error-decomposed barrier-margin result: a Q-Barrier-satisfying action leaves the next latent-budget state with an approximately budget-safe continuation under the learned critic, up to Bellman and latent-prediction errors. Across five safe ICRL benchmarks, the shield improves deployment-time reward-safety tradeoffs over a strong safe-ICRL baseline: after a short context window, it achieves higher return in four of five benchmarks while matching or lowering average episode cost in all five.

Minjae Kwon, Amir Moeini, Shangtong Zhang +1

University of Virginia

Reinforcement Learning Control Barrier Functions In-Context RL Safe RL

May 24, 2026cs.LG

Quantifying Empirical Compute-Supervision Tradeoffs in RLVR

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training language models, but in practice, verifiers are rarely perfect. Recent theoretical work predicts that verifier noise affects the rate of learning but not its final outcome, implying that sufficient compute should close any gap induced by imperfect supervision. We test this prediction empirically by post-training Qwen2.5 (0.5B, 1.5B) with GRPO on GSM8K while injecting controlled false-positive and false-negative noise into the binary correctness signal, and varying rollouts per prompt as a compute axis. In practice, the gap in validation accuracy persists under substantial compute scaling, with returns to compute that are sharply diminishing. We further find a structural asymmetry where false negatives monotonically degrade performance more quickly than false positives. These findings suggest verifier quality and training compute are not interchangeable, and that reducing false negatives is a more effective lever than scaling compute alone.

Ryo Mitsuhashi, Patrick Chen, Isabelle Tseng +2

1Princeton University

Reinforcement Learning RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards RL Post-Training

May 24, 2026cs.AI

Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat

As modern air combat evolves toward beyond-visual-range (BVR) multi-aircraft cooperative engagements, autonomous decision-making for unmanned combat aerial vehicles (UCAVs) faces significant challenges due to high-dimensional state spaces, discrete action commands, and strongly adversarial dynamic environments. To overcome the limitations of existing multi-agent reinforcement learning (MARL) methods in such settings, namely insufficient exploration efficiency, low sample utilization, and poor policy generalization, we propose Adversarial Curriculum and Evolutionary-enhanced Multi-agent Proximal Policy Optimization (ACE-MAPPO), a hybrid learning framework that integrates evolutionary algorithms with MAPPO. Specifically, a genetic soft update mechanism is introduced to enhance population diversity and mitigate convergence to local optima. An evolutionary-augmented prioritized trajectory replay strategy is further employed to improve the utilization of sparse high-value samples. In addition, an adversarial evolutionary curriculum learning mechanism is designed to enable adaptive training with progressively increasing difficulty. Extensive experimental results demonstrate that the proposed method outperforms MAPPO and other baseline algorithms in terms of training stability, convergence speed, and win rate, validating its effectiveness in multi-aircraft cooperative air combat scenarios.

Chengwei Li, Junlin Liu, Yang Gao

Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences

Multi-Agent Coordination Reinforcement Learning Curriculum RL Cooperative MARL

May 24, 2026cs.LG

A perspective on fluid mechanical environments for challenges in reinforcement learning

We consider the challenge of developing agents that efficiently interact with high-dimensional, evolving environments, towards a view of practical reinforcement learning (RL) agents interacting with open worlds, of which they witness and affect only a small part. We argue that canonical fluid mechanics problems, and their simulations, present a compelling testbed for the development of such methods. These problems arise in nonlinear instabilities, where small disturbances can grow to transform the dynamics of a system. Nonlinear instabilities represent several open scientific challenges with industrial applications -- the droplet breakup of a liquid jet, mixing at an interface between two fluids, and the appearance of unusually tall rogue waves in the ocean. In these settings, agents may leverage preserved representations across the changing dynamics to learn efficiently. We present two problem descriptions of agents interacting with a fluid mechanical environment, and describe the state and action spaces, and reward functions, for these agents. For these examples, we specify the aspects of the environment which are nonstationary and the preserved invariances. We note Dedalus and JAX-CFD as open-source simulators that can be used for the development of reinforcement learning methods (Burns et al., 2016; Kochkov et al., 2021)) We demonstrate the use of Dedalus for environment generation by creating RL agents that learn to navigate in a stationary environment that is simulated using Dedalus. This sets the stage for future development of RL agents that learn to meaningfully interact with simulated environments that represent scientific challenges in natural and industrial flows.

Shruti Mishra, Michael Chang, Vamsi Spandan +1

Sony AI · Cohere Labs Community · The Hebrew University of Jerusalem

RL Control Non-Stationary RL Reinforcement Learning

May 24, 2026cs.NI

Scaling up Energy-Aware Multi-Agent Reinforcement Learning for Mission-Oriented Drone Networks with Individual Reward

Multi-agent reinforcement learning (MARL) has shown wide applicability in collaborative systems such as autonomous driving and smart cities for its ability of learning through interaction. With the recent development of drone networks, researchers have also applied MARL to address the trajectory planning problems. However, the dynamic environment and the limited battery capacity are still challenging for using MARL to achieve efficient collaborative task execution. In this paper, we propose an energy-aware MARL model as an attempt to tackle these challenges, leveraging Deep Q-Networks (DQN) with \emph{individual reward functions} driven by the task execution progress and the remaining battery of drones. We conduct a set of simulation studies for the proposed mode and compare it with the shared reward MARL~\cite{Li2022MARL} to explore the impact of credit assignment in MARL. The results indicate that our proposed model can achieve at least 80% success rate regardless of the task locations and lengths. Similar to the shared reward mode, the individual reward mode can achieve a better success rate when the task density is high, and it can hit nearly a 100% success rate when task density gets close to 40%. The true advantage of our proposed model with individual reward is revealed when scaling up the environment. The comparison to the shared reward MARL shows that the our proposed model is more robust towards the change of the environment size and agent numbers. It can achieve higher success rate with fewer steps due to the clarity of the goal which improves energy efficiency even better.

Changling Li, Ying Li

Department of Computer Science, ETH Zurich, 8092, Zurich, Switzerland · Department of Computer Science, Colby College, 04901, Waterville, ME, USA

Reinforcement Learning Credit Assignment in RL Multi-Robot Coordination Cooperative MARL

May 24, 2026cs.LG

Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs

We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider log-linear softmax policies with linear function approximation, which extend the tabular softmax parameterization while retaining a tractable policy class. Under

Q^π_τ

-realizability for the regularized state-action value function, we first establish a non-uniform Polyak--Łojasiewicz (PŁ) inequality. The non-uniformity arises through degeneracy of constants associated with the policy geometry, namely the Fisher information matrix or an uncentered feature covariance matrix. We then identify two feature regimes under which this non-uniform constant can be bounded along the gradient flow. For full-affine-span features, we prove radial unboundedness of the KL regularizer and show that the smallest eigenvalue of the Fisher information matrix remains bounded below by an initialization-dependent positive constant. For simplex-valued features, we prove an analogous radial unboundedness result in the subspace orthogonal to the all-ones vector and obtain a uniform lower bound for the smallest eigenvalue of the uncentered covariance matrix. These results imply global linear convergence of the regularized objective along the gradient flow, i.e. suboptimality decaying as

\mathcal{O}(e^{-Ct})

for some

C>0

. Our analysis extends the global convergence theory of entropy-regularized softmax policy gradient beyond the tabular setting of Agarwal et al. (2020); Bhandari and Russo (2024); Mei et al. (2020).

Ziyue Chen, David Šiška, Lukasz Szpruch

Policy Gradient Reinforcement Learning Maximum Entropy RL Continuous-Time RL