{"total":78,"rows":[{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2402.02330","title":"Enhance Reasoning for Large Language Models in the Game Werewolf","created":"2024-02-04","cited_by_count":46,"area":"lr"},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2103.07927","title":"Modelling Behavioural Diversity for Learning in Open-Ended Games","created":"2021-03-14","cited_by_count":39,"area":null},{"id":"2312.00746","title":"Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games","created":"2023-12-01","cited_by_count":30,"area":"agents"},{"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":"2102.07659","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","created":"2021-02-15","cited_by_count":24,"area":null},{"id":"2302.07515","title":"TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play","created":"2023-02-15","cited_by_count":20,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","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":"2106.04958","title":"Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games","created":"2021-06-09","cited_by_count":14,"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":"2306.03034","title":"Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination","created":"2023-06-05","cited_by_count":12,"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":"2303.04096","title":"Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2207.10942","title":"Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation","created":"2022-07-22","cited_by_count":9,"area":null},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2505.23062","title":"Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data","created":"2025-05-29","cited_by_count":9,"area":"diffusion"},{"id":"2509.03682","title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","created":"2025-09-03","cited_by_count":9,"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":"2406.01103","title":"Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment","created":"2024-06-03","cited_by_count":8,"area":null},{"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":"2203.08412","title":"CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2501.01593","title":"BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems","created":"2025-01-03","cited_by_count":7,"area":"safety"},{"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":"2302.01049","title":"Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation","created":"2023-02-02","cited_by_count":6,"area":"distill"},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","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":"2309.01194","title":"A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects","created":"2023-09-03","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":"2209.10055","title":"Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games","created":"2022-09-21","cited_by_count":4,"area":null},{"id":"2212.00253","title":"Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2301.01609","title":"Emergent collective intelligence from massive-agent cooperation and competition","created":"2023-01-04","cited_by_count":4,"area":null},{"id":"2402.01111","title":"Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints","created":"2024-02-02","cited_by_count":4,"area":"deeprl"},{"id":"2407.03964","title":"Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2202.10134","title":"MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning","created":"2022-02-21","cited_by_count":3,"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":"2602.05327","title":"ProAct: Agentic Lookahead in Interactive Environments","created":"2026-02-05","cited_by_count":3,"area":"agents"},{"id":"2609.16679","title":"AI for Games in the Foundation Model Era","created":"2026-09-15","cited_by_count":3,"area":"wm"},{"id":"2102.12957","title":"Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2104.06687","title":"Reward function shape exploration in adversarial imitation learning: an empirical study","created":"2021-04-14","cited_by_count":2,"area":"offlinerl"},{"id":"2112.04785","title":"VMAgent: Scheduling Simulator for Reinforcement Learning","created":"2021-12-09","cited_by_count":2,"area":null},{"id":"2311.11537","title":"ADAPTER-RL: Adaptation of Any Agent using Reinforcement Learning","created":"2023-11-20","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":"2405.21027","title":"Fusion-PSRO: Nash Policy Fusion for Policy Space Response Oracles","created":"2024-05-31","cited_by_count":2,"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":"2112.13934","title":"RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2209.06904","title":"Forecasting Evolution of Clusters in Game Agents with Hebbian Learning","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2403.00841","title":"Offline Fictitious Self-Play for Competitive Games","created":"2024-02-29","cited_by_count":1,"area":"offlinerl"},{"id":"2404.07559","title":"Differentially Private Reinforcement Learning with Self-Play","created":"2024-04-11","cited_by_count":1,"area":"deeprl"},{"id":"2410.02231","title":"SEAL: SEmantic-Augmented Imitation Learning via Language Model","created":"2024-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2505.06319","title":"Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs","created":"2025-05-08","cited_by_count":1,"area":"deeprl"},{"id":"2112.08093","title":"Towards Controllable Agent in MOBA Games with Generative Modeling","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2206.11494","title":"CGAR: Critic Guided Action Redistribution in Reinforcement Leaning","created":"2022-06-23","cited_by_count":0,"area":null},{"id":"2304.13004","title":"Centralized control for multi-agent RL in a complex Real-Time-Strategy game","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2309.02869","title":"On Reducing Undesirable Behavior in Deep Reinforcement Learning Models","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2312.04245","title":"Mastering Complex Coordination through Attention-based Dynamic Graph","created":"2023-12-07","cited_by_count":0,"area":null},{"id":"2403.03172","title":"Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2406.04201","title":"Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games","created":"2024-06-06","cited_by_count":0,"area":null},{"id":"2410.14150","title":"Utilizing Large Language Models for Event Deconstruction to Enhance Multimodal Aspect-Based Sentiment Analysis","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2510.19528","title":"Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2602.00676","title":"OpenGuanDan: A Large-Scale Imperfect Information Game Benchmark","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2605.24343","title":"Adaptive Human-AI Coordination via Hierarchical Action Disentanglement","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2605.24352","title":"Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaboration","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2610.01882","title":"Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}