{"total":84,"rows":[{"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":"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":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"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":"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":"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":"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":"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":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2510.16097","title":"Narrowing Action Choices with AI Improves Human Sequential Decisions","created":"2025-10-17","cited_by_count":3,"area":null},{"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":"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":"2303.09628","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":"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":"2507.06628","title":"Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2605.07394","title":"BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2105.12328","title":"D2CFR: Minimize Counterfactual Regret with Deep Dueling Neural Network","created":"2021-05-26","cited_by_count":1,"area":null},{"id":"2109.02354","title":"Method for making multi-attribute decisions in wargames by combining intuitionistic fuzzy numbers with reinforcement learning","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2111.07631","title":"AI in Human-computer Gaming: Techniques, Challenges and Opportunities","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2204.07543","title":"CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2208.07753","title":"A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning","created":"2022-08-16","cited_by_count":1,"area":null},{"id":"2211.11616","title":"Learning Heterogeneous Agent Cooperation via Multiagent League Training","created":"2022-11-13","cited_by_count":1,"area":null},{"id":"2305.13824","title":"Constrained Reinforcement Learning for Dynamic Material Handling","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2306.15903","title":"Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs","created":"2023-06-28","cited_by_count":1,"area":null},{"id":"2310.20380","title":"Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2403.18056","title":"Self-Clustering Hierarchical Multi-Agent Reinforcement Learning with Extensible Cooperation Graph","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2407.03426","title":"Multi-Task Decision-Making for Multi-User 360 Video Processing over Wireless Networks","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2506.05702","title":"Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2102.08251","title":"Reinforced Contact Tracing and Epidemic Intervention","created":"2021-02-04","cited_by_count":0,"area":null},{"id":"2106.10305","title":"Multi-Task Learning for User Engagement and Adoption in Live Video Streaming Events","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2110.09035","title":"Edge Rewiring Goes Neural: Boosting Network Resilience without Rich Features","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2210.12896","title":"Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2301.10919","title":"Joint action loss for proximal policy optimization","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2304.10124","title":"Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning","created":"2023-04-20","cited_by_count":0,"area":null},{"id":"2402.00738","title":"FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game","created":"2024-02-01","cited_by_count":0,"area":null},{"id":"2403.18057","title":"Prioritized League Reinforcement Learning for Large-Scale Heterogeneous Multiagent Systems","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2409.00107","title":"Evaluating the Impact of Multiple DER Aggregators on Wholesale Energy Markets: A Hybrid Mean Field Approach","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2509.16020","title":"AI Methods for Permutation Circuit Synthesis Across Generic Topologies","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2512.12366","title":"ElasticVR: Elastic Task Computing in Multi-User Multi-Connectivity Wireless Virtual Reality (VR) Systems","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.16444","title":"StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.07521","title":"Pareto-guided Pipeline for Distilling Featherweight AI Agents in Mobile MOBA Games","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2607.06514","title":"FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.29983","title":"From Interests to Semantic IDs: Retrieval-Grounded Credit Assignment for Generative Recommendation","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.03372","title":"SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.18504","title":"How Low Can You Go: Fine-Tuning LLMs with Bayesian Optimization (LlMBO)","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18853","title":"Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}