{"total":161,"rows":[{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79,"area":"offlinerl"},{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75,"area":"lr"},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2509.02333","title":"DCPO: Dynamic Clipping Policy Optimization","created":"2025-09-02","cited_by_count":40,"area":"lr"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2409.15355","title":"Block-Attention for Efficient Prefilling","created":"2024-09-14","cited_by_count":37,"area":"rag"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2209.08483","title":"Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26,"area":"deeprl"},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2509.11452","title":"Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting","created":"2025-09-14","cited_by_count":23,"area":"alignment"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2407.14931","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","created":"2024-07-20","cited_by_count":21,"area":null},{"id":"2510.06062","title":"When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2406.03704","title":"Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking","created":"2024-06-06","cited_by_count":19,"area":"deeprl"},{"id":"2205.09284","title":"Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble","created":"2022-05-19","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2203.10603","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","created":"2022-03-20","cited_by_count":17,"area":null},{"id":"2312.12065","title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","created":"2023-12-19","cited_by_count":17,"area":null},{"id":"2111.04051","title":"Coordinated Proximal Policy Optimization","created":"2021-11-07","cited_by_count":16,"area":null},{"id":"2302.00965","title":"Visual Imitation Learning with Patch Rewards","created":"2023-02-02","cited_by_count":16,"area":"offlinerl"},{"id":"2004.00981","title":"Benchmarking End-to-End Behavioural Cloning on Video Games","created":"2020-04-02","cited_by_count":15,"area":"offlinerl"},{"id":"2203.16406","title":"PerfectDou: Dominating DouDizhu with Perfect Information Distillation","created":"2022-03-30","cited_by_count":15,"area":null},{"id":"2207.02702","title":"Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2209.00347","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","created":"2022-09-01","cited_by_count":14,"area":null},{"id":"2108.05030","title":"DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks","created":"2021-08-11","cited_by_count":13,"area":"driving"},{"id":"2209.10081","title":"Revisiting Discrete Soft Actor-Critic","created":"2022-09-21","cited_by_count":13,"area":null},{"id":"2106.00517","title":"Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment","created":"2021-06-01","cited_by_count":12,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2212.01105","title":"Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery","created":"2022-12-02","cited_by_count":12,"area":"offlinerl"},{"id":"2207.05683","title":"Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2306.06799","title":"On the Efficacy of 3D Point Cloud Reinforcement Learning","created":"2023-06-11","cited_by_count":11,"area":null},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11,"area":"offlinerl"},{"id":"2505.12504","title":"CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models","created":"2025-05-18","cited_by_count":11,"area":"lr"},{"id":"2508.02833","title":"TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback","created":"2025-08-04","cited_by_count":11,"area":"lr"},{"id":"2402.02053","title":"Affordable Generative Agents","created":"2024-02-03","cited_by_count":9,"area":"agents"},{"id":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2503.13356","title":"Agents Play Thousands of 3D Video Games","created":"2025-03-17","cited_by_count":9,"area":"agents"},{"id":"2202.04337","title":"Scenario-Assisted Deep Reinforcement Learning","created":"2022-02-09","cited_by_count":8,"area":null},{"id":"2211.03352","title":"Curriculum-based Asymmetric Multi-task Reinforcement Learning","created":"2022-11-07","cited_by_count":8,"area":null},{"id":"2212.01737","title":"RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning","created":"2022-12-04","cited_by_count":8,"area":null},{"id":"2312.14472","title":"Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2010.01112","title":"FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization","created":"2020-10-02","cited_by_count":7,"area":"offlinerl"},{"id":"2106.10411","title":"Boosting Offline Reinforcement Learning with Residual Generative Modeling","created":"2021-06-19","cited_by_count":7,"area":"offlinerl"},{"id":"2110.14221","title":"Learning Diverse Policies in MOBA Games via Macro-Goals","created":"2021-10-27","cited_by_count":7,"area":null},{"id":"2203.06416","title":"Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems","created":"2022-03-12","cited_by_count":7,"area":null},{"id":"2203.08412","title":"CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2204.02558","title":"DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2403.15267","title":"Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies","created":"2024-03-22","cited_by_count":7,"area":"deeprl"},{"id":"2505.15211","title":"GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2508.21365","title":"Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models","created":"2025-08-29","cited_by_count":7,"area":"lr"},{"id":"2509.09177","title":"Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL","created":"2025-09-11","cited_by_count":7,"area":null},{"id":"2603.21065","title":"LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning","created":"2026-03-22","cited_by_count":7,"area":"agents"},{"id":"2604.07853","title":"QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2112.11216","title":"Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2204.12750","title":"DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games","created":"2022-04-27","cited_by_count":6,"area":null},{"id":"2312.02561","title":"DanZero+: Dominating the GuanDan Game through Reinforcement Learning","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2312.06258","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2402.00046","title":"Introducing PetriRL: An Innovative Framework for JSSP Resolution Integrating Petri nets and Event-based Reinforcement Learning","created":"2024-01-23","cited_by_count":6,"area":"deeprl"},{"id":"2410.14468","title":"Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Making","created":"2024-10-18","cited_by_count":6,"area":"driving"},{"id":"2603.14389","title":"From $\\log \\pi$ to $\\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2210.17087","title":"DanZero: Mastering GuanDan Game with Reinforcement Learning","created":"2022-10-31","cited_by_count":5,"area":null},{"id":"2304.11632","title":"Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective","created":"2023-04-23","cited_by_count":5,"area":null},{"id":"2401.16444","title":"Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain","created":"2024-01-28","cited_by_count":5,"area":null},{"id":"2402.17773","title":"SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks","created":"2024-02-17","cited_by_count":5,"area":"deeprl"},{"id":"2505.11875","title":"J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2110.13799","title":"Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2311.04686","title":"Robust and Communication-Efficient Federated Domain Adaptation via Random Features","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2505.03344","title":"RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulation","created":"2025-05-06","cited_by_count":4,"area":null},{"id":"2506.03757","title":"PPO in the Fisher-Rao geometry","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2207.07971","title":"A Survey of Decision Making in Adversarial Games","created":"2022-07-16","cited_by_count":3,"area":null},{"id":"2302.02299","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","created":"2023-02-05","cited_by_count":3,"area":null},{"id":"2306.15503","title":"Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning","created":"2023-06-27","cited_by_count":3,"area":"offlinerl"},{"id":"2404.04772","title":"Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking Learning","created":"2024-04-07","cited_by_count":3,"area":"deeprl"},{"id":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2501.04538","title":"HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2507.06615","title":"Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2507.23698","title":"Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents","created":"2025-07-31","cited_by_count":3,"area":"agents"},{"id":"2510.16097","title":"Narrowing Action Choices with AI Improves Human Sequential Decisions","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2512.22322","title":"SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents","created":"2025-12-26","cited_by_count":3,"area":"agents"},{"id":"2603.04918","title":"BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2605.01248","title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data","created":"2026-05-02","cited_by_count":3,"area":"lr"},{"id":"2607.10169","title":"Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization","created":"2026-07-11","cited_by_count":3,"area":"lr"},{"id":"2607.29078","title":"DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2102.10774","title":"Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning","created":"2021-02-22","cited_by_count":2,"area":"offlinerl"},{"id":"2105.08666","title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2208.03002","title":"A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning","created":"2022-08-05","cited_by_count":2,"area":null},{"id":"2303.07046","title":"Deploying Offline Reinforcement Learning with Human Feedback","created":"2023-03-13","cited_by_count":2,"area":"alignment"},{"id":"2303.09628","title":"Efficient Learning of High Level Plans from Play","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2303.16737","title":"Multi-Agent Reinforcement Learning with Action Masking for UAV-enabled Mobile Communications","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2312.01090","title":"Self Generated Wargame AI: Double Layer Agent Task Planning Based on Large Language Model","created":"2023-12-02","cited_by_count":2,"area":"agents"},{"id":"2402.12685","title":"XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques","created":"2024-02-20","cited_by_count":2,"area":"deeprl"},{"id":"2406.19720","title":"CUPID: Improving Battle Fairness and Position Satisfaction in Online MOBA Games with a Re-matchmaking System","created":"2024-06-28","cited_by_count":2,"area":null},{"id":"2503.17985","title":"Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree","created":"2025-03-23","cited_by_count":2,"area":"deeprl"},{"id":"2507.06628","title":"Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":null}],"next_cursor":"100"}