{"total":15,"rows":[{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85,"area":"offlinerl"},{"id":"2010.14876","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","created":"2020-10-28","cited_by_count":71,"area":"offlinerl"},{"id":"1906.09510","title":"Learning Belief Representations for Imitation Learning in POMDPs","created":"2019-06-22","cited_by_count":24,"area":"offlinerl"},{"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":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2303.02646","title":"Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation","created":"2023-03-05","cited_by_count":6,"area":"offlinerl"},{"id":"2501.12633","title":"Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors","created":"2025-01-22","cited_by_count":6,"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":"2304.00977","title":"Selective Reincarnation: Offline-to-Online Multi-Agent Reinforcement Learning","created":"2023-03-31","cited_by_count":2,"area":"offlinerl"},{"id":"2508.01167","title":"T2S: Tokenized Skill Scaling for Lifelong Imitation Learning","created":"2025-08-02","cited_by_count":2,"area":"offlinerl"},{"id":"2403.04221","title":"Why Online Reinforcement Learning is Causal","created":"2024-03-07","cited_by_count":1,"area":"offlinerl"},{"id":"2103.05895","title":"WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata","created":"2021-03-10","cited_by_count":0,"area":"offlinerl"},{"id":"2104.02661","title":"Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning","created":"2021-04-06","cited_by_count":0,"area":"offlinerl"},{"id":"2504.17891","title":"Do We Need Transformers to Play FPS Video Games?","created":"2025-04-24","cited_by_count":0,"area":"offlinerl"},{"id":"2606.19481","title":"Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning","created":"2026-06-17","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}