{"total":79,"rows":[{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89,"area":"offlinerl"},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2305.17330","title":"MADiff: Offline Multi-agent Learning with Diffusion Models","created":"2023-05-27","cited_by_count":75,"area":"diffusion"},{"id":"2202.06239","title":"Supported Policy Optimization for Offline Reinforcement Learning","created":"2022-02-13","cited_by_count":74,"area":"offlinerl"},{"id":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61,"area":"offlinerl"},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43,"area":"offlinerl"},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37,"area":"offlinerl"},{"id":"2110.09796","title":"Offline Reinforcement Learning with Value-based Episodic Memory","created":"2021-10-19","cited_by_count":36,"area":"offlinerl"},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36,"area":"offlinerl"},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2302.14372","title":"The In-Sample Softmax for Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":33,"area":"offlinerl"},{"id":"2112.02845","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","created":"2021-12-06","cited_by_count":32,"area":"offlinerl"},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2305.17198","title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem","created":"2023-05-26","cited_by_count":19,"area":"offlinerl"},{"id":"2302.07549","title":"Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications","created":"2023-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2107.01460","title":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","created":"2021-07-03","cited_by_count":16,"area":null},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2206.03383","title":"On the Role of Discount Factor in Offline Reinforcement Learning","created":"2022-06-07","cited_by_count":16,"area":"offlinerl"},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2307.01472","title":"Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL","created":"2023-07-04","cited_by_count":15,"area":"diffusion"},{"id":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2211.15612","title":"Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning","created":"2022-11-28","cited_by_count":12,"area":"offlinerl"},{"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":"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":"2302.13493","title":"The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning","created":"2023-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2311.02194","title":"AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation","created":"2023-11-03","cited_by_count":10,"area":"offlinerl"},{"id":"2402.08421","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","created":"2024-02-13","cited_by_count":10,"area":"offlinerl"},{"id":"2511.05005","title":"Multi-agent Coordination via Flow Matching","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2406.09068","title":"Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation","created":"2024-06-13","cited_by_count":9,"area":"offlinerl"},{"id":"2407.20164","title":"Language-Conditioned Offline RL for Multi-Robot Navigation","created":"2024-07-29","cited_by_count":9,"area":"offlinerl"},{"id":"2302.00521","title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","created":"2023-02-01","cited_by_count":8,"area":"offlinerl"},{"id":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2508.06269","title":"OM2P: Offline Multi-Agent Mean-Flow Policy","created":"2025-08-08","cited_by_count":8,"area":"offlinerl"},{"id":"2211.08016","title":"Contextual Transformer for Offline Meta Reinforcement Learning","created":"2022-11-15","cited_by_count":7,"area":"offlinerl"},{"id":"2306.08900","title":"Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization","created":"2023-06-15","cited_by_count":7,"area":"offlinerl"},{"id":"2509.15172","title":"Self-Improvement of Language Models by Post-Training on Multi-Agent Debate","created":"2025-09-18","cited_by_count":7,"area":"agents"},{"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":"2312.03644","title":"MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment","created":"2023-12-06","cited_by_count":6,"area":"offlinerl"},{"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":"2410.01101","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","created":"2024-10-01","cited_by_count":6,"area":"offlinerl"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2210.04251","title":"State Advantage Weighting for Offline RL","created":"2022-10-09","cited_by_count":5,"area":"offlinerl"},{"id":"2407.01343","title":"Coordination Failure in Cooperative Offline MARL","created":"2024-07-01","cited_by_count":5,"area":"offlinerl"},{"id":"2310.04579","title":"Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":4,"area":"agents"},{"id":"2409.12001","title":"Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning","created":"2024-09-18","cited_by_count":4,"area":"offlinerl"},{"id":"2502.18955","title":"Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset","created":"2025-02-26","cited_by_count":4,"area":"offlinerl"},{"id":"2505.05968","title":"Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition","created":"2025-05-09","cited_by_count":4,"area":"offlinerl"},{"id":"2406.02890","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2410.19450","title":"Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration","created":"2024-10-25","cited_by_count":3,"area":"offlinerl"},{"id":"2505.18595","title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","created":"2025-05-24","cited_by_count":3,"area":"agents"},{"id":"2604.08174","title":"Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning","created":"2026-04-09","cited_by_count":3,"area":"offlinerl"},{"id":"2302.09605","title":"Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning","created":"2023-02-19","cited_by_count":2,"area":"offlinerl"},{"id":"2509.21828","title":"Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2025-09-26","cited_by_count":2,"area":"agents"},{"id":"2601.07463","title":"Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning","created":"2026-01-12","cited_by_count":2,"area":"wm"},{"id":"2603.08399","title":"A Recipe for Stable Offline Multi-agent Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"offlinerl"},{"id":"2605.01457","title":"CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making","created":"2026-05-02","cited_by_count":2,"area":"offlinerl"},{"id":"2402.12845","title":"MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces","created":"2024-02-20","cited_by_count":1,"area":"offlinerl"},{"id":"2403.00841","title":"Offline Fictitious Self-Play for Competitive Games","created":"2024-02-29","cited_by_count":1,"area":"offlinerl"},{"id":"2501.18138","title":"B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning","created":"2025-01-30","cited_by_count":1,"area":"offlinerl"},{"id":"2502.08985","title":"Beyond Shallow Behavior: Task-Efficient Value-Based Multi-Task Offline MARL via Skill Discovery","created":"2025-02-13","cited_by_count":1,"area":"offlinerl"},{"id":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2603.11691","title":"STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement Learning","created":"2026-03-12","cited_by_count":1,"area":"offlinerl"},{"id":"2604.07072","title":"Epistemic Robust Offline Reinforcement Learning","created":"2026-04-08","cited_by_count":1,"area":"offlinerl"},{"id":"2412.19064","title":"Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding","created":"2024-12-26","cited_by_count":0,"area":null},{"id":"2603.28573","title":"Learning Partial Action Replacement in Offline MARL","created":"2026-03-30","cited_by_count":0,"area":"offlinerl"},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.23308","title":"CODA: Coordination via On-Policy Diffusion for Multi-Agent Offline Reinforcement Learning","created":"2026-04-25","cited_by_count":0,"area":"offlinerl"},{"id":"2605.01356","title":"Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2606.21085","title":"Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2606.25389","title":"Offline Multi-agent Continual Cooperation via Skill Partition and Reuse","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.03667","title":"Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning","created":"2026-09-03","cited_by_count":0,"area":"offlinerl"},{"id":"2609.31281","title":"MA-WAM: Multi-Agent World-Action Model for Test-Time Planning","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2609.31286","title":"G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies","created":"2026-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2609.32594","title":"MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32827","title":"Improving LLM Collaboration via Multi-Agent Preference Learning","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.02554","title":"Test-time Multi-agent Coordination by Decomposed Value Gradient Flow","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}