{"total":14,"rows":[{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2103.08050","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","created":"2021-03-14","cited_by_count":238,"area":"offlinerl"},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2106.03155","title":"SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching","created":"2021-06-06","cited_by_count":14,"area":"offlinerl"},{"id":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13,"area":"offlinerl"},{"id":"2203.11409","title":"A Primer on Maximum Causal Entropy Inverse Reinforcement Learning","created":"2022-03-22","cited_by_count":13,"area":"offlinerl"},{"id":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10,"area":"offlinerl"},{"id":"2306.15156","title":"Learning non-Markovian Decision-Making from State-only Sequences","created":"2023-06-27","cited_by_count":6,"area":"offlinerl"},{"id":"2112.15364","title":"Robust Entropy-regularized Markov Decision Processes","created":"2021-12-31","cited_by_count":4,"area":"offlinerl"},{"id":"2201.01874","title":"Combining Reinforcement Learning and Inverse Reinforcement Learning for Asset Allocation Recommendations","created":"2022-01-06","cited_by_count":3,"area":"offlinerl"},{"id":"2602.17832","title":"MePoly: Max Entropy Polynomial Policy Optimization","created":"2026-02-19","cited_by_count":3,"area":"offlinerl"},{"id":"2503.11019","title":"Residual Policy Gradient: A Reward View of KL-regularized Objective","created":"2025-03-14","cited_by_count":2,"area":"offlinerl"}],"next_cursor":null}