{"total":69,"rows":[{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662,"area":"offlinerl"},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2210.03112","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","created":"2022-10-06","cited_by_count":60,"area":"offlinerl"},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48,"area":"offlinerl"},{"id":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46,"area":"offlinerl"},{"id":"2105.10037","title":"Cross-domain Imitation from Observations","created":"2021-05-20","cited_by_count":42,"area":"offlinerl"},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2302.14372","title":"The In-Sample Softmax for Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":33,"area":"offlinerl"},{"id":"2109.05413","title":"Learning Selective Communication for Multi-Agent Path Finding","created":"2021-09-12","cited_by_count":32,"area":"offlinerl"},{"id":"2206.00159","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","created":"2022-06-01","cited_by_count":30,"area":"offlinerl"},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26,"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":"1803.05402","title":"Imitation Learning with Concurrent Actions in 3D Games","created":"2018-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"2602.15010","title":"BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames","created":"2026-02-16","cited_by_count":18,"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":"1803.01129","title":"OIL: Observational Imitation Learning","created":"2018-03-03","cited_by_count":11,"area":"offlinerl"},{"id":"2010.03691","title":"Regularized Inverse Reinforcement Learning","created":"2020-10-07","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":"2310.09426","title":"Offline Reinforcement Learning for Optimizing Production Bidding Policies","created":"2023-10-13","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":"1907.02140","title":"Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model","created":"2019-07-03","cited_by_count":7,"area":"offlinerl"},{"id":"2310.20663","title":"Offline RL with Observation Histories: Analyzing and Improving Sample Complexity","created":"2023-10-31","cited_by_count":7,"area":"offlinerl"},{"id":"2404.12530","title":"TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents","created":"2024-04-18","cited_by_count":7,"area":"offlinerl"},{"id":"2505.03209","title":"DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning","created":"2025-05-06","cited_by_count":7,"area":"offlinerl"},{"id":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2312.03446","title":"Visual Hindsight Self-Imitation Learning for Interactive Navigation","created":"2023-12-05","cited_by_count":6,"area":"offlinerl"},{"id":"2102.05547","title":"Learning Equational Theorem Proving","created":"2021-02-10","cited_by_count":5,"area":"offlinerl"},{"id":"2201.02381","title":"Offline Reinforcement Learning for Road Traffic Control","created":"2022-01-07","cited_by_count":5,"area":"offlinerl"},{"id":"2001.07798","title":"Augmenting GAIL with BC for sample efficient imitation learning","created":"2020-01-21","cited_by_count":4,"area":"offlinerl"},{"id":"2106.08199","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","created":"2021-06-15","cited_by_count":4,"area":"offlinerl"},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4,"area":"offlinerl"},{"id":"2408.11632","title":"Optimizing Interpretable Decision Tree Policies for Reinforcement Learning","created":"2024-08-21","cited_by_count":4,"area":"offlinerl"},{"id":"2410.15910","title":"Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning","created":"2024-10-21","cited_by_count":4,"area":"offlinerl"},{"id":"2109.07275","title":"DROMO: Distributionally Robust Offline Model-based Policy Optimization","created":"2021-09-15","cited_by_count":3,"area":"offlinerl"},{"id":"2207.07790","title":"BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion","created":"2022-07-16","cited_by_count":3,"area":"offlinerl"},{"id":"2403.19462","title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","created":"2024-03-28","cited_by_count":3,"area":"offlinerl"},{"id":"2505.11719","title":"Zero-Shot Visual Generalization in Robot Manipulation","created":"2025-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2505.20621","title":"Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning","created":"2025-05-27","cited_by_count":3,"area":"offlinerl"},{"id":"2103.14823","title":"Co-Imitation Learning without Expert Demonstration","created":"2021-03-27","cited_by_count":2,"area":"offlinerl"},{"id":"2310.10312","title":"End-to-end Offline Reinforcement Learning for Glycemia Control","created":"2023-10-16","cited_by_count":2,"area":"offlinerl"},{"id":"2404.04682","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","created":"2024-04-06","cited_by_count":2,"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"},{"id":"2008.00766","title":"Tracking the Race Between Deep Reinforcement Learning and Imitation Learning -- Extended Version","created":"2020-08-03","cited_by_count":1,"area":"offlinerl"},{"id":"2104.00123","title":"Generalized Reinforcement Learning for Building Control using Behavioral Cloning","created":"2021-03-31","cited_by_count":1,"area":"offlinerl"},{"id":"2110.03165","title":"Offline RL With Resource Constrained Online Deployment","created":"2021-10-07","cited_by_count":1,"area":"offlinerl"},{"id":"2205.05784","title":"Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II","created":"2022-05-11","cited_by_count":1,"area":"offlinerl"},{"id":"2311.13326","title":"Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series","created":"2023-11-22","cited_by_count":1,"area":"offlinerl"},{"id":"2408.06818","title":"Personalized Dynamic Difficulty Adjustment -- Imitation Learning Meets Reinforcement Learning","created":"2024-08-13","cited_by_count":1,"area":"offlinerl"},{"id":"2510.00922","title":"On Discovering Algorithms for Adversarial Imitation Learning","created":"2025-10-01","cited_by_count":1,"area":"offlinerl"},{"id":"1906.05467","title":"Imitation Learning of Neural Spatio-Temporal Point Processes","created":"2019-06-13","cited_by_count":0,"area":"offlinerl"},{"id":"2002.01059","title":"Preventing Imitation Learning with Adversarial Policy Ensembles","created":"2020-01-31","cited_by_count":0,"area":"offlinerl"},{"id":"2009.09577","title":"Learn to Exceed: Stereo Inverse Reinforcement Learning with Concurrent Policy Optimization","created":"2020-09-21","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":"2112.08094","title":"Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloning","created":"2021-12-15","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":"2209.13489","title":"Reward Learning using Structural Motifs in Inverse Reinforcement Learning","created":"2022-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2307.00125","title":"RObotic MAnipulation Network (ROMAN) -- Hybrid Hierarchical Learning for Solving Complex Sequential Tasks","created":"2023-06-30","cited_by_count":0,"area":"offlinerl"},{"id":"2408.10113","title":"Enhancing Reinforcement Learning Through Guided Search","created":"2024-08-19","cited_by_count":0,"area":"offlinerl"},{"id":"2506.15654","title":"CAWR: Corruption-Averse Advantage-Weighted Regression for Robust Policy Optimization","created":"2025-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2509.03206","title":"Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback","created":"2025-09-03","cited_by_count":0,"area":"offlinerl"},{"id":"2510.15189","title":"RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation","created":"2025-10-16","cited_by_count":0,"area":"offlinerl"},{"id":"2605.00159","title":"E$^2$DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation","created":"2026-04-30","cited_by_count":0,"area":"offlinerl"},{"id":"2608.15770","title":"Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}