Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Reinforcement learning studies how an agent can choose actions over time to earn rewards, using experience to improve its decisions. Common approaches include value-based methods such as Q-learning, policy-gradient methods such as PPO, and model-based methods that learn or use a model of the environment; offline and hierarchical methods address learning from fixed data and long tasks. Applications range from Atari and MuJoCo benchmarks to robot control, traffic, games, and language-model agents that use tools or solve multi-step problems. A central challenge is making learning efficient and reliable when rewards are sparse or imperfect, environments change, and success in simulation or benchmarks may not transfer safely to deployment.

Latest papers

1,742 papers237 papers in the last four weeks, up 46% on the four weeks before. 1.4% of all new papers.

Mar 2, 2026

Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents

Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluency and compliance. Conventional reinforcement learning often merges these heterogeneous goals into a single reward, causing high-magnitude session-level rewards to overwhelm subtler turn-level signals, which leads to unstable training or reward hacking. To address this issue, we propose Dual-Horizon Credit Assignment (DuCA), a framework that disentangles optimization across time scales. Its core, Horizon-Independent Advantage Normalization (HIAN), separately normalizes advantages from turn-level and session-level rewards before fusion, ensuring balanced gradient contributions from both immediate and long-term objectives to the policy update. Extensive experiments with a high-fidelity user simulator show DuCA outperforms the state-of-the-art GRPO baseline, achieving a 6.82% relative improvement in conversion rate, reducing inter-sentence repetition by 82.28%, and lowering identity detection rate by 27.35%, indicating a substantial improvement for an industrial sales scenario that effectively balances the dual demands of strategic performance and naturalistic language generation.

Haojin Yang, Ai Jian, Xinyue Huang +5

Peking University · Beijing University of Posts and Telecommunications · Sun Yat-sen University +2

RL for LLM Agents Reinforcement Learning Credit Assignment in RL RL Fine-Tuning Step-Level Credit Assignment in RL Conversational Agents

Mar 2, 2026

SubstratumGraphEnv: Reinforcement Learning Environment (RLE) for Modeling System Attack Paths

Automating network security analysis, particularly the identification of potential attack paths, presents significant challenges. Due in part to the sequential, interconnected, and evolutionary nature of system events which most artificial intelligence (AI) techniques struggle to model effectively. This paper proposes a Reinforcement Learning (RL) environment generation framework that simulates the sequence of processes executed on a Windows operating system, enabling dynamic modeling of malicious processes on a system. This methodology models operating system state and transitions using a graph representation. This graph is derived from open-source System Monitor (Sysmon) logs. To address the variety in system event types, fields, and log formats, a mechanism was developed to capture and model parent-child processes from Sysmon logs. A Gymnasium environment (SubstratumGraphEnv) was constructed to establish the perceptible basis for an RL environment, and a customized PyTorch interface was also built (SubstratumBridge) to translate Gymnasium graphs into Deep Reinforcement Learning (DRL) observations and discrete actions. Graph Convolutional Networks (GCNs) concretize the graph's local and global state, which feed the distinct policy and critic heads of an Advantage Actor-Critic (A2C) model. This work's central contribution lies in the design of a novel deep graphical RL environment that automates translation of sequential user and system events, furnishing crucial context for cybersecurity analysis. This work provides a foundation for future research into shaping training parameters and advanced reward shaping, while also offering insight into which system events attributes are critical to training autonomous RL agents.

Bahirah Adewunmi, Edward Raff, Sanjay Purushotham

University of Maryland, Baltimore County · CrowdStrike

Reinforcement Learning Autonomous Cyber Defense

Mar 1, 2026

PAC Guarantees for Reinforcement Learning: Sample Complexity, Coverage, and Structure

When data is scarce or mistakes are costly, average-case metrics fall short. What a practitioner needs is a guarantee: with probability at least

1-δ

, the learned policy is

\varepsilon

-close to optimal after

N

episodes. This is the PAC promise, and between 2018 and 2025 the RL theory community made striking progress on when such promises can be kept. We survey that progress. Our organizing tool is the Coverage-Structure-Objective (CSO) framework, proposed here, which decomposes nearly every PAC sample complexity result into three factors: coverage (how data were obtained), structure (intrinsic MDP or function-class complexity), and objective (what the learner must deliver). CSO is not a theorem but an interpretive template that identifies bottlenecks and makes cross-setting comparison immediate. The technical core covers tight tabular baselines and the uniform-PAC bridge to regret; structural complexity measures (Bellman rank, witness rank, Bellman-Eluder dimension) governing learnability with function approximation; results for linear, kernel/NTK, and low-rank models; reward-free exploration as upfront coverage investment; and pessimistic offline RL where inherited coverage is the binding constraint. We provide practitioner tools: rate lookup tables indexed by CSO coordinates, Bellman residual diagnostics, coverage estimation with deployment gates, and per-episode policy certificates. A final section catalogs open problems, separating near-term targets from frontier questions where coverage, structure, and computation tangle in ways current theory cannot resolve.

Joshua Steier

Function Approximation in RL Reinforcement Learning Sample-Efficient RL

Mar 1, 2026

Hybrid TD3: Overestimation Bias Analysis and Stable Policy Optimization for Hybrid Action Space

Reinforcement learning in discrete-continuous hybrid action spaces presents fundamental challenges for robotic manipulation, where high-level task decisions and low-level joint-space execution must be jointly optimized. Existing approaches either discretize continuous components or relax discrete choices into continuous approximations, which suffer from scalability limitations and training instability in high-dimensional action spaces and under domain randomization. In this paper, we propose Hybrid TD3, an extension of Twin Delayed Deep Deterministic Policy Gradient (TD3) that natively handles parameterized hybrid action spaces in a principled manner. We conduct a rigorous theoretical analysis of overestimation bias in hybrid action settings, deriving formal bounds under twin-critic architectures and establishing a complete bias ordering across five algorithmic variants under synchronized Gaussian error assumptions. Building on this analysis, we introduce a weighted clipped Q-learning target that marginalizes over the discrete action distribution, achieving equivalent bias reduction to standard clipped minimization while improving policy smoothness. Experimental results demonstrate that Hybrid TD3 achieves superior training stability and competitive performance against state-of-the-art hybrid action baselines.

Thanh-Tuan Tran, Thanh Nguyen Canh, Nak Young Chong +1

University of Engineering and Technology, Vietnam National University, 10000, Hanoi, Vietnam. · School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, 923-1211, Ishikawa, Japan. · Department of Robotics, Hanyang University, Ansan, 15588, Gyeonggi, Korea.

Hybrid Action Space RL Reinforcement Learning Robotic RL Deep Deterministic Policy Gradient

Mar 1, 2026

The Informational Cost of Agency: A Bounded Measure of Interaction Efficiency for Deployed Reinforcement Learning

Deployed reinforcement learning systems lack a principled runtime reliability theory. We close this gap by introducing Bipredictability, P, a closed form information theoretic metric that quantifies how efficiently a closed loop interaction between agent and environment converts uncertainty into shared predictability. P admits a provable classical bound P equal, smaller than 0.5, derived from Shannon entropy subadditivity, and responsive agency necessarily suppresses P below this ceiling, a structural prediction we term the informational cost of agency. Across 21 trained continuous control agents, we confirm this prediction empirically at P = 0.33 plus minus 0.02. The same suppression signature reproduces in language model dialogue, convolutional vision systems, and classical mechanical baselines, indicating that P captures a substrate independent property of agentic interaction rather than an algorithm specific artifact. The Information Digital Twin, IDT, a model agnostic architecture that computes P from the external interaction stream, detects 89.3% of coupling degradations against 44.0% for reward based monitoring, with 4.4 times lower latency. P provides the missing measurement layer for runtime reliability and closed loop self regulation in deployed autonomous systems.

Wael Hafez, Cameron Reid, Amit Nazeri

Semarx Research LLC Alexandria, VA, USA.

AI Agent Reliability Reinforcement Learning

Mar 1, 2026

Intent-Context Synergy Reinforcement Learning for Autonomous UAV Decision-Making in Air Combat

Autonomous UAV infiltration in dynamic contested environments remains a significant challenge due to the partially observable nature of threats and the conflicting objectives of mission efficiency versus survivability. Traditional Reinforcement Learning (RL) approaches often suffer from myopic decision-making and struggle to balance these trade-offs in real-time. To address these limitations, this paper proposes an Intent-Context Synergy Reinforcement Learning (ICS-RL) framework. The framework introduces two core innovations: (1) An LSTM-based Intent Prediction Module that forecasts the future trajectories of hostile units, transforming the decision paradigm from reactive avoidance to proactive planning via state augmentation; (2) A Context-Analysis Synergy Mechanism that decomposes the mission into hierarchical sub-tasks (safe cruise, stealth planning, and hostile breakthrough). We design a heterogeneous ensemble of Dueling DQN agents, each specialized in a specific tactical context. A dynamic switching controller based on Max-Advantage values seamlessly integrates these agents, allowing the UAV to adaptively select the optimal policy without hard-coded rules. Extensive simulations demonstrate that ICS-RL significantly outperforms baselines (Standard DDQN) and traditional methods (PSO, Game Theory). The proposed method achieves a mission success rate of 88% and reduces the average exposure frequency to 0.24 per episode, validating its superiority in ensuring robust and stealthy penetration in high-dynamic scenarios.

Jiahao Fu, Feng Yang

National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an, Shanxi, China · School of Automation, Northwestern Polytechnical University, Xi’an, Shanxi, China

Reinforcement Learning Partially Observable RL Deep Q-Learning Hierarchical RL

Mar 1, 2026

Stabilizing Policy Optimization via Logits Convexity

While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unstable, especially when compared to supervised fine-tuning (SFT). In this work, we investigate the stability gap between SFT and RL from a gradient-based perspective, and show that the convexity of the SFT loss with respect to model logits plays a key role in enabling stable training. Our theoretical analysis demonstrates that this property induces favorable gradient directionality during optimization. In contrast, Proximal Policy Optimization (PPO), a widely adopted policy gradient algorithm utilizing a clipped surrogate objective, lacks this stabilizing property. Motivated by this observation, we propose Logits Convex Optimization (LCO), a simple yet effective policy optimization framework that aligns the learned policy with an optimal target derived from the original RL objective, thereby emulating the stabilizing effects of logits-level convexity. Extensive experiments across multiple model families show that our LCO framework consistently improves training stability and outperforms conventional RL methods on a broad range of benchmarks.

Hongzhan Chen, Tao Yang, Yuhua Zhu +3

School of Computer Science and Engineering, Sun Yat-sen University, China · Shanghai Innovation Institute · Wechat Search, Tencent Inc, China +1

Policy Optimization Reinforcement Learning RL Fine-Tuning Policy Gradient Methods Proximal Policy Optimization

Mar 1, 2026

Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning

Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a fast learner and a meta learner to address continual Reinforcement Learning~(RL) problems. These two learners are coupled to perform distinct yet complementary roles: the fast learner focuses on knowledge transfer, while the meta learner ensures knowledge integration. In contrast to traditional multi-task RL approaches that share knowledge through average return maximization, our meta learner incrementally integrates new experiences by explicitly minimizing catastrophic forgetting, thereby supporting efficient cumulative knowledge transfer for the fast learner. To facilitate rapid adaptation in new environments, we introduce an adaptive meta warm-up mechanism that selectively harnesses past knowledge. We conduct experiments in various pixel-based and continuous control benchmarks, revealing the superior performance of continual learning for our proposed dual-learner approach relative to baseline methods. The code is released in https://github.com/datake/FAME.

Ke Sun, Hongming Zhang, Jun Jin +4

University of Alberta · National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institution of Automation, Chinese Academy of Sciences · Edmonton Research Center, Huawei Canada +2

Reinforcement Learning Continual RL Meta-Reinforcement Learning Catastrophic Forgetting

Feb 28, 2026

Learning to Attack: A Bandit Approach to Adversarial Context Poisoning

Neural contextual bandits are vulnerable to adversarial attacks, where subtle perturbations to rewards, actions, or contexts induce suboptimal decisions. We introduce AdvBandit, a black-box adaptive attack that formulates context poisoning as a continuous-armed bandit problem, enabling the attacker to jointly learn and exploit the victim's evolving policy. The attacker requires no access to the victim's internal parameters, reward function, or gradient information; instead, it constructs a surrogate model using a maximum-entropy inverse reinforcement learning module from observed context-action pairs and optimizes perturbations against this surrogate using projected gradient descent. An upper confidence bound-aware Gaussian process guides arm selection. An attack-budget control mechanism is also introduced to limit detection risk and overhead. We provide theoretical guarantees, including sublinear attacker regret and lower bounds on victim regret linear in the number of attacks. Experiments on three real-world datasets (Yelp, MovieLens, and Disin) against various victim contextual bandits demonstrate that our attack model achieves higher cumulative victim regret than state-of-the-art baselines.

Ray Telikani, Amir H. Gandomi

Data Science Institute, University of Technology Sydney, NSW, Australia

Black-Box Adversarial Attacks Adversarial Bandits Reinforcement Learning

Feb 28, 2026

Multi-Agent Reinforcement Learning for Dynamic Pricing: Balancing Profitability,Stability and Fairness

Dynamic pricing in competitive retail markets requires strategies that adapt to fluctuating demand and competitor behavior. In this work, we present a systematic empirical evaluation of multi-agent reinforcement learning (MARL) approaches-specifically MAPPO and MADDPG-for dynamic price optimization under competition. Using a simulated marketplace environment derived from real-world retail data, we benchmark these algorithms against an Independent DDPG (IDDPG) baseline, a widely used independent learner in MARL literature. We evaluate profit performance, stability across random seeds, fairness, and training efficiency. Our results show that MAPPO consistently achieves the highest average returns with low variance, offering a stable and reproducible approach for competitive price optimization, while MADDPG achieves slightly lower profit but the fairest profit distribution among agents. These findings demonstrate that MARL methods-particularly MAPPO-provide a scalable and stable alternative to independent learning approaches for dynamic retail pricing.

Krishna Kumar Neelakanta Pillai Santha Kumari Amma

Dynamic Pricing Reinforcement Learning Multi-Agent Reinforcement Learning

Feb 27, 2026

Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning

Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a fixed dataset of state-action trajectories. We consider the problem in a mixed-motive multiagent setting, where the goal is to solve a game under the offline learning constraint. We first frame this problem in terms of selecting among candidate equilibria. Since datasets may inform only a small fraction of game dynamics, it is generally infeasible in offline game-solving to even verify a proposed solution is a true equilibrium. Therefore, we consider the relative probability of low regret (i.e., closeness to equilibrium) across candidates based on the information available. Specifically, we extend Policy Space Response Oracles (PSRO), an online game-solving approach, by quantifying game dynamics uncertainty and modifying the RL objective to skew towards solutions more likely to have low regret in the true game. We further propose a novel meta-strategy solver, tailored for the offline setting, to guide strategy exploration in PSRO. Our incorporation of Conservatism principles from Offline reinforcement learning approaches for strategy Exploration gives our approach its name: COffeE-PSRO. Experiments demonstrate COffeE-PSRO's ability to extract lower-regret solutions than state-of-the-art offline approaches and reveal relationships between algorithmic components empirical game fidelity, and overall performance.

Austin A. Nguyen, Michael P. Wellman

University of Michigan

Reinforcement Learning Game Theory Conservative RL Offline RL Multi-Agent Reinforcement Learning Game-Theoretic RL

Feb 27, 2026

Online World Modeling Enables Real-World Inverse Reinforcement Learning from Observation

Current methods in robot learning are fundamentally bottlenecked by one or more of: hand-designed rewards, simulation modeling, or action supervision (e.g. teleoperation) each requiring significant domain expertise, engineering effort, and robot-operator labor. Towards reducing these bottlenecks, this work pursues observational learning via Inverse Reinforcement Learning from Observation (IRLfO) in which only access to task observations (e.g. video) is assumed. Due to the challenging setting and limitations of RL methods, IRLfO has thus far remained impractical for real-world robot learning. Here, we present the first IRL method to learn visual manipulation in the real world from scratch, and the first real-world demonstration of positive online transfer across visual manipulation tasks from scratch. In under 40 minutes, MPAIL2 learns pick-and-place from scratch to 82%, where RL and BC with equal interaction and demonstration budgets reach only 0% and 12% despite their reward and action supervision. Interactive project page with training videos: https://uwrobotlearning.github.io/mpail2/

Tyler Han, Bat Nemekhbold, Siyang Shen +6

University of Washington

Robot Learning from Video Reinforcement Learning Robotic Manipulation Robot Imitation Learning

Feb 27, 2026

Bridging Dynamics Gaps via Diffusion Schrödinger Bridge for Cross-Domain Reinforcement Learning

Cross-domain reinforcement learning (RL) aims to learn transferable policies under dynamics shifts between source and target domains. A key challenge lies in the lack of target-domain environment interaction and reward supervision, which prevents direct policy learning. To address this challenge, we propose Bridging Dynamics Gaps for Cross-Domain Reinforcement Learning (BDGxRL), a novel framework that leverages Diffusion Schrödinger Bridge (DSB) to align source transitions with target-domain dynamics encoded in offline demonstrations. Moreover, we introduce a reward modulation mechanism that estimates rewards based on state transitions, applying to DSB-aligned samples to ensure consistency between rewards and target-domain dynamics. BDGxRL performs target-oriented policy learning entirely within the source domain, without access to the target environment or its rewards. Experiments on MuJoCo cross-domain benchmarks demonstrate that BDGxRL outperforms state-of-the-art baselines and shows strong adaptability under transition dynamics shifts.

Hanping Zhang, Yuhong Guo

School of Computer Science, Carleton University, Ottawa, Canada

Reinforcement Learning Cross-Domain Transfer Learning

Feb 26, 2026

Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning

Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. However, existing approaches face a fundamental credit assignment problem: methods like Search-R1 assign a single outcome reward to the entire multi-step trajectory, providing no signal about which reasoning or retrieval decisions were responsible for success or failure. Process-reward methods such as StepSearch introduce step-level supervision but still sample complete trajectories independently, so advantage estimates at any given step are contaminated by the randomness of all other steps. We propose SLATE (Step-Level Advantage estimation for Truncated Exploration), which addresses both problems through two complementary ideas. First, truncated step-level sampling generates k continuations from a shared prefix, isolating all variation to a single decision point. We prove this reduces the variance of advantage estimates by up to a factor of T compared to full-trajectory sampling for T-step trajectories, the first formal variance guarantee for step-level RL in retrieval-augmented reasoning. Second, dense, decomposed process rewards separately evaluate reasoning quality, query quality, and answer correctness on a ternary scale via an LLM judge, providing richer supervision than binary outcome signals or heuristic step-level scores. Experiments on seven QA benchmarks show that SLATE consistently outperforms both sparse-reward and process-reward baselines, achieving a 7.0% relative improvement over Search-R1 on the 7B model and 30.7% on the 3B model. Gains are largest on challenging multi-hop tasks, and ablations confirm that truncated sampling and dense rewards provide complementary benefits.

Chris Samarinas, Haw-Shiuan Chang, Hamed Zamani

Center for Intelligent Information Retrieval University of Massachusetts Amherst Amherst, MA, United States

Reinforcement Learning Process Reward Models RL for Language Model Reasoning Step-Level Credit Assignment in RL Agentic RAG

Feb 26, 2026

A Model-Free Universal AI

In general reinforcement learning, all established optimal agents, including AIXI, are model-based, explicitly maintaining and using environment models. This paper introduces Universal AI with Q-Induction (AIQI), the first model-free agent proven to be asymptotically

\varepsilon

-optimal in general RL. AIQI performs universal induction over distributional action-value functions, instead of policies or environments like previous works. Under a grain of truth condition, we prove that AIQI is strong asymptotically

\varepsilon

-optimal and asymptotically

\varepsilon

-Bayes-optimal. We also apply our novel proof techniques to show asymptotic

\varepsilon

-optimality of Self-AIXI without any ad-hoc assumptions. Our results significantly expand the diversity of known universal agents.

Yegon Kim, Juho Lee

Graduate School of AI, KAIST, Seoul, South Korea

Reinforcement Learning Bayesian RL Model-Free RL

Feb 26, 2026

GeoWorld: Geometric World Models

Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather than generating pixels. However, existing approaches face two major challenges: (i) their latent representations are typically learned in Euclidean space, neglecting the underlying geometric and hierarchical structure among states, and (ii) they struggle with long-horizon prediction, which leads to rapid degradation across extended rollouts. To address these challenges, we introduce GeoWorld, a geometric world model that preserves geometric structure and hierarchical relations through a Hyperbolic JEPA, which maps latent representations from Euclidean space onto hyperbolic manifolds. We further introduce Geometric Reinforcement Learning for energy-based optimization, enabling stable multi-step planning in hyperbolic latent space. Extensive experiments on CrossTask and COIN demonstrate around 3% SR improvement in 3-step planning and 2% SR improvement in 4-step planning compared to the state-of-the-art V-JEPA 2. Project website: https://steve-zeyu-zhang.github.io/GeoWorld.

Zeyu Zhang, Danning Li, Ian Reid +1

ANU · MBZUAI

World Model Learning World Models World Model-Based Planning Energy-Based Models Reinforcement Learning

Feb 26, 2026

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization

Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the discovery of novel states. We propose Exploratory Memory-Augmented On- and Off-Policy Optimization (EMPO

^2

), a hybrid RL framework that leverages memory for exploration and combines on- and off-policy updates to make LLMs perform well with memory while also ensuring robustness without it. On ScienceWorld and WebShop, EMPO

^2

achieves 128.6% and 11.3% improvements over GRPO, respectively. Moreover, in out-of-distribution tests, EMPO

^2

demonstrates superior adaptability to new tasks, requiring only a few trials with memory and no parameter updates. These results highlight EMPO

^2

as a promising framework for building more exploratory and generalizable LLM-based agents.

Zeyuan Liu, Jeonghye Kim, Xufang Luo +2

Microsoft Research · KAIST

RL for LLM Agents Reinforcement Learning RL Exploration Memory-Augmented Language Model Agents Off-Policy RL

Feb 26, 2026

Learning to Generate Secure Code via Token-Level Rewards

Large language models (LLMs) have demonstrated strong capabilities in code generation, yet they remain prone to producing security vulnerabilities. Existing approaches commonly suffer from two key limitations: the scarcity of high-quality security data and coarse-grained reinforcement learning reward signals. To address these challenges, we propose Vul2Safe, a new secure code generation framework that leverages LLM self-reflection to construct high-confidence repair pairs from real-world vulnerabilities, and further generates diverse implicit prompts to build the PrimeVul+ dataset. Meanwhile, we introduce SRCode, a novel training framework that pioneers the use of token-level rewards in reinforcement learning for code security, which enables the model to continuously attend to and reinforce critical fine-grained security patterns during training. Compared with traditional instance-level reward schemes, our approach allows for more precise optimization of local security implementations. Extensive experiments show that PrimeVul+ and SRCode substantially reduce security vulnerabilities in generated code while improving overall code quality across multiple benchmarks.

Jiazheng Quan, Xiaodong Li, Bin Wang +5

Fuyao University of Science and Technology · Xiamen University · Peking University +1

Secure Code Generation RL for Code Generation Reinforcement Learning

Feb 26, 2026

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

Value decomposition (VD) methods have achieved remarkable success in cooperative multi-agent reinforcement learning (MARL). However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic Q-value overestimation. This issue is particularly severe in MARL due to the combinatorial explosion of the joint action space, which often results in unstable learning and suboptimal policies. To address this problem, we propose QSIM, a similarity weighted Q-learning framework that reconstructs the TD target using action similarity. Instead of using the greedy joint action directly, QSIM forms a similarity weighted expectation over a structured near-greedy joint action space. This formulation allows the target to integrate Q-values from diverse yet behaviorally related actions while assigning greater influence to those that are more similar to the greedy choice. By smoothing the target with structurally relevant alternatives, QSIM effectively mitigates overestimation and improves learning stability. Extensive experiments demonstrate that QSIM can be seamlessly integrated with various VD methods, consistently yielding superior performance and stability compared to the original algorithms. Furthermore, empirical analysis confirms that QSIM significantly mitigates the systematic value overestimation in MARL. Code is available at https://github.com/MaoMaoLYJ/pymarl-qsim.

Yuanjun Li, Bin Zhang, Hao Chen +3

Shandong University · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences · Li Auto Inc. +1

Reinforcement Learning Cooperative MARL Q-Learning

Feb 25, 2026

Learning Rewards, Not Labels: Adversarial Inverse Reinforcement Learning for Machinery Fault Detection

Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple guessing game (Contextual Bandits). To bridge this gap, we formulate MFD as an offline inverse reinforcement learning problem, where the agent learns the reward dynamics directly from healthy operational sequences, thereby bypassing the need for manual reward engineering and fault labels. Our framework employs Adversarial Inverse Reinforcement Learning to train a discriminator that distinguishes between normal (expert) and policy-generated transitions. The discriminator's learned reward serves as an anomaly score, indicating deviations from normal operating behaviour. When evaluated on three run-to-failure benchmark datasets (HUMS2023, IMS, and XJTU-SY), the model consistently assigns low anomaly scores to normal samples and high scores to faulty ones, enabling early and robust fault detection. By aligning RL's sequential reasoning with MFD's temporal structure, this work opens a path toward RL-based diagnostics in data-driven industrial settings.

Dhiraj Neupane, Richard Dazeley, Mohamed Reda Bouadjenek +1

Deakin University Waurn Ponds, Victoria, Australia

Fault Detection Unsupervised Anomaly Detection Reinforcement Learning

Feb 25, 2026

Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization

Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models. Extending these methods to multimodal settings, however, faces a critical challenge: the instability of std-based normalization, which is easily distorted by extreme samples with nearly positive or negative rewards. Unlike pure-text LLMs, multimodal models are particularly sensitive to such distortions, as both perceptual and reasoning errors influence their responses. To address this, we characterize each sample by its difficulty, defined through perceptual complexity (measured via visual entropy) and reasoning uncertainty (captured by model confidence). Building on this characterization, we propose difficulty-aware group normalization (Durian), which re-groups samples by difficulty levels and shares the std within each group. Our approach preserves GRPO's intra-group distinctions while eliminating sensitivity to extreme cases, yielding significant performance gains across multiple multimodal reasoning benchmarks.

Jinghan Li, Junfeng Fang, Jinda Lu +5

University of Science and Technology of China · National University of Singapore

Multimodal Large Language Models Multimodal Reasoning RL for VLMs Reinforcement Learning Group Relative Policy Optimization

Feb 25, 2026

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable, often leading to training collapse. This instability limits scalability to larger environments and longer interaction horizons, and constrains systematic exploration of algorithmic design choices. In this paper, we first propose ARLArena, a stable training recipe and systematic analysis framework that examines training stability in a controlled and reproducible setting. ARLArena first constructs a clean and standardized testbed. Then, we decompose policy gradient into four core design dimensions and assess the performance and stability of each dimension. Through this fine-grained analysis, we distill a unified perspective on ARL and propose SAMPO, a stable agentic policy optimization method designed to mitigate the dominant sources of instability in ARL. Empirically, SAMPO achieves consistently stable training and strong performance across diverse agentic tasks. Overall, this study provides a unifying policy gradient perspective for ARL and offers practical guidance for building stable and reproducible LLM-based agent training pipelines.

Xiaoxuan Wang, Han Zhang, Haixin Wang +11

Department of Computer Science, University of California, Los Angeles, California, USA · University of Wisconsin–Madison, Madison, Wisconsin, USA

Agentic RL Reinforcement Learning Policy Gradient Methods LLM Agent Training Policy Learning RL Stability

Feb 25, 2026

GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL: rollouts are generated by an evolving policy, and learning is shaped by exploration and reward feedback, unlike supervised fine-tuning (SFT) with fixed trajectories. As a result, prior work often relies on manual curation or simple heuristic filters (e.g., accuracy), which can admit incorrect or low-utility problems. We propose GradAlign, a gradient-aligned data selection method for LLM reinforcement learning that uses a small, trusted validation set to prioritize training problems whose policy gradients align with validation gradients, yielding an adaptive curriculum. We evaluate GradAlign across three challenging data regimes: unreliable reward signals, distribution imbalance, and low-utility training corpus, showing that GradAlign consistently outperforms existing baselines, underscoring the importance of directional gradient signals in navigating non-stationary policy optimization and yielding more stable training and improved final performance. We release our implementation at https://github.com/StigLidu/GradAlign

Ningyuan Yang, Weihua Du, Weiwei Sun +2

Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University · Language Technologies Institute (LTI), Carnegie Mellon University

RL for Language Models Reinforcement Learning Training Data Selection Curriculum RL

Feb 24, 2026

On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation

Reinforcement learning (RL) agents under partial observability often condition actions on internally accumulated information such as memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with respect to internal information under fixed observations. This induces a probe-relative notion of

ε

-behavioural equivalence and a within-policy behavioural distance that quantifies probe sensitivity. We establish three structural results. First, the set of policies exhibiting non-trivial behavioural dependency is not closed under convex aggregation. Second, behavioural distance contracts under convex combination. Third, we prove a sufficient local condition under which gradient ascent on a skewed mixture objective decreases behavioural distance when a dominant-mode gradient aligns with the direction of steepest contraction. Minimal bandit and partially observable gridworld experiments provide controlled witnesses of these mechanisms. In the examined settings, behavioural distance decreases under convex aggregation and under continued optimisation with skewed latent priors, and in these experiments it precedes degradation under latent prior shift. These results identify structural conditions under which probe-conditioned behavioural separation is not preserved under common policy transformations.

Alexander Galozy

Center for Applied Intelligent Systems Research, Halmstad University, Sweden

Reinforcement Learning Partially Observable RL Policy Learning

Feb 24, 2026

Regret-Guided Search Control for Efficient Learning in AlphaZero

Reinforcement learning (RL) agents achieve remarkable performance but remain far less learning-efficient than humans. While RL agents require extensive self-play games to extract useful signals, humans often need only a few games, improving rapidly by repeatedly revisiting states where mistakes occurred. This idea, known as search control, aims to restart from valuable states rather than always from the initial state. In AlphaZero, prior work Go-Exploit applies this idea by sampling past states from self-play or search trees, but it treats all states equally, regardless of their learning potential. We propose Regret-Guided Search Control (RGSC), which extends AlphaZero with a regret network that learns to identify high-regret states, where the agent's evaluation diverges most from the actual outcome. These states are collected from both self-play trajectories and MCTS nodes, stored in a prioritized regret buffer, and reused as new starting positions. Across 9x9 Go, 10x10 Othello, and 11x11 Hex, RGSC outperforms AlphaZero and Go-Exploit by an average of 77 and 89 Elo, respectively. When training on a well-trained 9x9 Go model, RGSC further improves the win rate against KataGo from 69.3% to 78.2%, while both baselines show no improvement. These results demonstrate that RGSC provides an effective mechanism for search control, improving both efficiency and robustness of AlphaZero training. Our code is available at https://rlg.iis.sinica.edu.tw/papers/rgsc.

Yun-Jui Tsai, Wei-Yu Chen, Yan-Ru Ju +2

Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan · College of Computing, Georgia Institute of Technology

Reinforcement Learning Game-Playing Agents Sample-Efficient RL Self-Play RL

Feb 24, 2026

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in Constrained Markov Decision Process (CMDP) form) is equivalent to solving distributionally robust safe RL problems (in robust CMDP form), effectively avoiding min-max optimization. Empirical analyses on safe-control-gym and safety-gymnasium scenarios demonstrate that Fuz-RL effectively integrates with existing safe RL baselines in a model-free manner, significantly improving both safety and control performance under various types of uncertainties in observation, action, and dynamics.

Xu Wan, Chao Yang, Cheng Yang +2

Zhejiang University · Alibaba DAMO Academy · Peking University

Safe RL Reinforcement Learning Constrained RL Distributionally Robust RL Model-Free RL

Feb 24, 2026

TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer

Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research introduces a transformative framework for generating large-scale urban mobility trajectories, employing a novel application of a transformer-based model pre-trained and fine-tuned through a two-phase process. Initially, trajectory generation is conceptualized as an offline reinforcement learning (RL) problem, with a significant reduction in vocabulary space achieved during tokenization. The integration of Inverse Reinforcement Learning (IRL) allows for the capture of trajectory-wise reward signals, leveraging historical data to infer individual mobility preferences. Subsequently, the pre-trained model is fine-tuned using the constructed reward model, effectively addressing the challenges inherent in traditional RL-based autoregressive methods, such as long-term credit assignment and handling of sparse reward environments. Comprehensive evaluations on multiple datasets illustrate that our framework markedly surpasses existing models in terms of reliability and diversity. Our findings not only advance the field of urban mobility modeling but also provide a robust methodology for simulating urban data, with significant implications for traffic management and urban development planning. The implementation is publicly available at https://github.com/Wangjw6/TrajGPT_R.

Jiawei Wang, Chuang Yang, Jiawei Yong +6

The University of Tokyo, Tokyo 113-0034, Japan · Toyota Motor Corporation, Tokyo 112-0004, Japan

Trajectory Generation RL for Generative Models Reinforcement Learning

Feb 24, 2026

A Generalized Apprenticeship Learning Framework for Capturing Evolving Student Pedagogical Strategies

Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) have advanced rapidly in recent years and have been successfully applied to e-learning environments like intelligent tutoring systems (ITSs). Despite great success, the broader application of DRL to educational technologies has been limited due to major challenges such as sample inefficiency and difficulty designing the reward function. In contrast, Apprenticeship Learning (AL) uses a few expert demonstrations to infer the expert's underlying reward functions and derive decision-making policies that generalize and replicate optimal behavior. In this work, we leverage a generalized AL framework, THEMES, to induce effective pedagogical policies by capturing the complexities of the expert student learning process, where multiple reward functions may dynamically evolve over time. We evaluate the effectiveness of THEMES against six state-of-the-art baselines, demonstrating its superior performance and highlighting its potential as a powerful alternative for inducing effective pedagogical policies and show that it can achieve high performance, with an AUC of 0.899 and a Jaccard of 0.653, using only 18 trajectories of a previous semester to predict student pedagogical decisions in a later semester.

Md Mirajul Islam, Xi Yang, Adittya Soukarjya Saha +2

North Carolina State University, Raleigh, NC 27606, USA · IBM Research, Yorktown Heights, NY 10598, USA

AI in Education Policy Learning Reinforcement Learning

Feb 23, 2026

Cross domain Persistent Monitoring for Hybrid Aerial Underwater Vehicles

Hybrid Unmanned Aerial Underwater Vehicles (HUAUVs) have emerged as platforms capable of operating in both aerial and underwater environments, enabling applications such as inspection, mapping, search, and rescue in challenging scenarios. However, the development of novel methodologies poses significant challenges due to the distinct dynamics and constraints of the air and water domains. In this work, we present persistent monitoring tasks for HUAUVs by combining Deep Reinforcement Learning (DRL) and Transfer Learning to enable cross-domain adaptability. Our approach employs a shared DRL architecture trained on Lidar sensor data (on air) and Sonar data (underwater), demonstrating the feasibility of a unified policy for both environments. We further show that the methodology presents promising results, taking into account the uncertainty of the environment and the dynamics of multiple mobile targets. The proposed framework lays the groundwork for scalable autonomous persistent monitoring solutions based on DRL for hybrid aerial-underwater vehicles.

Ricardo B. Grando, Victor A. Kich, Alisson H. Kolling +3

Robotics Underwater Robotics Reinforcement Learning Aerial Robotics

Feb 23, 2026

Understanding Gap-Dependent Regret for Optimism-Based Reinforcement Learning with Linear Function Approximation

We study gap-dependent regret for reinforcement learning with linear function approximation. While prior works have established gap-dependent guarantees in this setting, existing analyses do not apply to algorithms that achieve the nearly minimax-optimal worst-case regret bound

\tilde{O}(d\sqrt{H^3K})

, where

d

is the feature dimension,

H

is the horizon length, and

K

is the number of episodes. We bridge this gap by establishing the first gap-dependent regret bound for the nearly minimax-optimal algorithm LSVI-UCB++ (He et al., 2023), with an expected regret bound

\tilde{O}(d^2H^3/Δ_{\min}+d^6H^5)

, improving the dependence on both

d

and

H

in the leading gap-dependent term compared with previous results. To understand the exploration cost induced by optimism, we establish a structural lower bound

Ω(d^2H^3/Δ_{\min})

for a broad class of algorithms based on persistent ellipsoidal optimism. When specialized to LSVI-UCB++, this result shows that the leading dependence of our upper bound on

d

,

H

, and

Δ_{\min}

is tight up to logarithmic factors. Beyond this algorithmic class, we establish a general gap-dependent lower bound

Ω(dH^3\log K/Δ_{\min})

for arbitrary learning algorithms, showing that the logarithmic dependence on

K

and the cubic dependence on

H

are intrinsic to gap-dependent expected regret in linear MDPs. Together, our results substantially narrow the gap between upper and lower bounds and provide a sharper characterization of gap-dependent learning and optimism-based exploration with linear function approximation.

Haochen Zhang, Zhong Zheng, Lingzhou Xue

Department of Statistics, The Pennsylvania State University · Department of Applied and Computational Mathematics and Statistics, University of Notre Dame

Regret Minimization in RL Reinforcement Learning Linear Markov Decision Processes