{"total":83,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452,"area":"offlinerl"},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"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":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193,"area":"offlinerl"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85,"area":"offlinerl"},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69,"area":"offlinerl"},{"id":"2106.03498","title":"Identifiability in inverse reinforcement learning","created":"2021-06-07","cited_by_count":55,"area":"offlinerl"},{"id":"2006.14154","title":"Strictly Batch Imitation Learning by Energy-based Distribution Matching","created":"2020-06-25","cited_by_count":54,"area":"offlinerl"},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2004.09395","title":"Energy-Based Imitation Learning","created":"2020-04-20","cited_by_count":40,"area":"offlinerl"},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40,"area":"offlinerl"},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"1905.11108","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","created":"2019-05-27","cited_by_count":28,"area":"offlinerl"},{"id":"2111.01365","title":"Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics","created":"2021-11-02","cited_by_count":27,"area":"offlinerl"},{"id":"1812.00950","title":"Generative Adversarial Self-Imitation Learning","created":"2018-12-03","cited_by_count":25,"area":"offlinerl"},{"id":"2006.13258","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization","created":"2020-06-23","cited_by_count":22,"area":"offlinerl"},{"id":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22,"area":"offlinerl"},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2207.01166","title":"Target-absent Human Attention","created":"2022-07-04","cited_by_count":20,"area":"offlinerl"},{"id":"2304.13774","title":"Distance Weighted Supervised Learning for Offline Interaction Data","created":"2023-04-26","cited_by_count":18,"area":"offlinerl"},{"id":"2310.00678","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","created":"2023-10-01","cited_by_count":18,"area":"offlinerl"},{"id":"2109.04307","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","created":"2021-09-09","cited_by_count":15,"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":"2210.01282","title":"Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":12,"area":"offlinerl"},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2402.01886","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","created":"2024-02-02","cited_by_count":11,"area":"offlinerl"},{"id":"1805.08336","title":"Maximum Causal Tsallis Entropy Imitation Learning","created":"2018-05-22","cited_by_count":10,"area":"offlinerl"},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2410.14069","title":"Rethinking Optimal Transport in Offline Reinforcement Learning","created":"2024-10-17","cited_by_count":9,"area":"offlinerl"},{"id":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","cited_by_count":9,"area":"offlinerl"},{"id":"1808.07903","title":"LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations","created":"2018-08-23","cited_by_count":8,"area":"offlinerl"},{"id":"2104.14654","title":"Adversarial Inverse Reinforcement Learning for Mean Field Games","created":"2021-04-29","cited_by_count":8,"area":"offlinerl"},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2209.10149","title":"Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation","created":"2022-09-21","cited_by_count":7,"area":"offlinerl"},{"id":"2407.00898","title":"Residual-MPPI: Online Policy Customization for Continuous Control","created":"2024-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7,"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":"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":"2206.09498","title":"Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning","created":"2022-06-19","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19946","title":"Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^\\pi$-Realizable MDPs","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2509.21172","title":"Inverse Reinforcement Learning with Just Classification and a Few Regressions","created":"2025-09-25","cited_by_count":5,"area":"offlinerl"},{"id":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"1911.00238","title":"Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning","created":"2019-11-01","cited_by_count":4,"area":"offlinerl"},{"id":"2112.15364","title":"Robust Entropy-regularized Markov Decision Processes","created":"2021-12-31","cited_by_count":4,"area":"offlinerl"},{"id":"2208.04919","title":"Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience","created":"2022-08-09","cited_by_count":4,"area":"offlinerl"},{"id":"2101.00186","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","created":"2021-01-01","cited_by_count":3,"area":"offlinerl"},{"id":"2103.02863","title":"Inverse Reinforcement Learning with Explicit Policy Estimates","created":"2021-03-04","cited_by_count":3,"area":"offlinerl"},{"id":"2210.12272","title":"Implicit Offline Reinforcement Learning via Supervised Learning","created":"2022-10-21","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":"1906.04813","title":"Towards Inverse Reinforcement Learning for Limit Order Book Dynamics","created":"2019-06-11","cited_by_count":2,"area":"offlinerl"},{"id":"2111.07667","title":"Versatile Inverse Reinforcement Learning via Cumulative Rewards","created":"2021-11-15","cited_by_count":2,"area":"offlinerl"},{"id":"2007.07443","title":"Deep PQR: Solving Inverse Reinforcement Learning using Anchor Actions","created":"2020-07-15","cited_by_count":1,"area":"offlinerl"},{"id":"2209.13224","title":"Regularized Soft Actor-Critic for Behavior Transfer Learning","created":"2022-09-27","cited_by_count":1,"area":"offlinerl"},{"id":"2311.15920","title":"A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning","created":"2023-11-27","cited_by_count":1,"area":"offlinerl"},{"id":"2412.11155","title":"Partial Identifiability in Inverse Reinforcement Learning For Agents With Non-Exponential Discounting","created":"2024-12-15","cited_by_count":1,"area":"offlinerl"},{"id":"2503.17865","title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","created":"2025-03-22","cited_by_count":1,"area":"offlinerl"},{"id":"2509.12010","title":"Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids","created":"2025-09-15","cited_by_count":1,"area":"offlinerl"},{"id":"2509.23135","title":"Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm","created":"2025-09-27","cited_by_count":1,"area":"offlinerl"},{"id":"2004.00993","title":"Augmented Q Imitation Learning (AQIL)","created":"2020-03-31","cited_by_count":0,"area":"offlinerl"},{"id":"2209.08947","title":"Age of Semantics in Cooperative Communications: To Expedite Simulation Towards Real via Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":0,"area":"offlinerl"},{"id":"2401.16772","title":"Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator","created":"2024-01-30","cited_by_count":0,"area":"offlinerl"},{"id":"2405.02243","title":"Towards Improving Learning from Demonstration Algorithms via MCMC Methods","created":"2024-05-03","cited_by_count":0,"area":"offlinerl"},{"id":"2409.18051","title":"Inverse Reinforcement Learning with Multiple Planning Horizons","created":"2024-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2410.07643","title":"On Reward Transferability in Adversarial Inverse Reinforcement Learning: Insights from Random Matrix Theory","created":"2024-10-10","cited_by_count":0,"area":"offlinerl"},{"id":"2501.12785","title":"On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration","created":"2025-01-22","cited_by_count":0,"area":"offlinerl"},{"id":"2510.03830","title":"HOFLON: Hybrid Offline Learning and Online Optimization for Process Start-Up and Grade-Transition Control","created":"2025-10-04","cited_by_count":0,"area":"offlinerl"},{"id":"2512.06956","title":"Statistical analysis of Inverse Entropy-regularized Reinforcement Learning","created":"2025-12-07","cited_by_count":0,"area":"offlinerl"},{"id":"2601.23010","title":"Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement Learning","created":"2026-01-30","cited_by_count":0,"area":"offlinerl"},{"id":"2602.17632","title":"SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"id":"2604.22873","title":"When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning","created":"2026-04-23","cited_by_count":0,"area":"offlinerl"},{"id":"2605.08131","title":"Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization","created":"2026-05-01","cited_by_count":0,"area":"offlinerl"},{"id":"2609.15883","title":"Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport","created":"2026-09-14","cited_by_count":0,"area":"offlinerl"},{"id":"2610.00758","title":"Scalable Multi-Task Inverse Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}