{"total":60,"rows":[{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214,"area":"offlinerl"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90,"area":"offlinerl"},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2103.09575","title":"Regularized Behavior Value Estimation","created":"2021-03-17","cited_by_count":32,"area":"offlinerl"},{"id":"2103.01948","title":"Offline Reinforcement Learning with Pseudometric Learning","created":"2021-03-02","cited_by_count":28,"area":"offlinerl"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2210.09241","title":"Boosting Offline Reinforcement Learning via Data Rebalancing","created":"2022-10-17","cited_by_count":22,"area":"offlinerl"},{"id":"2306.13085","title":"Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting","created":"2023-06-22","cited_by_count":22,"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":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","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":"2011.13467","title":"Episodic Self-Imitation Learning with Hindsight","created":"2020-11-26","cited_by_count":10,"area":"offlinerl"},{"id":"2310.07433","title":"Imitation Learning from Observation with Automatic Discount Scheduling","created":"2023-10-11","cited_by_count":10,"area":"offlinerl"},{"id":"2201.10070","title":"MOORe: Model-based Offline-to-Online Reinforcement Learning","created":"2022-01-25","cited_by_count":9,"area":"offlinerl"},{"id":"2110.14355","title":"Transfer learning with causal counterfactual reasoning in Decision Transformers","created":"2021-10-27","cited_by_count":8,"area":"offlinerl"},{"id":"2210.05125","title":"Human-AI Coordination via Human-Regularized Search and Learning","created":"2022-10-11","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":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"2410.15698","title":"Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces","created":"2024-10-21","cited_by_count":6,"area":"offlinerl"},{"id":"1910.12154","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","created":"2019-10-26","cited_by_count":5,"area":"offlinerl"},{"id":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","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":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2502.07937","title":"Active Advantage-Aligned Online Reinforcement Learning with Offline Data","created":"2025-02-11","cited_by_count":5,"area":"offlinerl"},{"id":"2110.14464","title":"Learning from demonstrations with SACR2: Soft Actor-Critic with Reward Relabeling","created":"2021-10-27","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":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","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":"1805.04969","title":"Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning","created":"2018-05-13","cited_by_count":3,"area":"offlinerl"},{"id":"2001.06944","title":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","created":"2020-01-20","cited_by_count":3,"area":"offlinerl"},{"id":"2111.14346","title":"Pessimistic Model Selection for Offline Deep Reinforcement Learning","created":"2021-11-29","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":"2211.16838","title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation","created":"2022-11-30","cited_by_count":3,"area":"offlinerl"},{"id":"2306.15503","title":"Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning","created":"2023-06-27","cited_by_count":3,"area":"offlinerl"},{"id":"2411.10268","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","created":"2024-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2503.11339","title":"Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model","created":"2025-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2512.10510","title":"Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning","created":"2025-12-11","cited_by_count":3,"area":"offlinerl"},{"id":"2103.05904","title":"Combining Learning from Demonstration with Learning by Exploration to Facilitate Contact-Rich Tasks","created":"2021-03-10","cited_by_count":2,"area":"offlinerl"},{"id":"2312.17168","title":"Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?","created":"2023-12-28","cited_by_count":2,"area":"offlinerl"},{"id":"2406.03069","title":"\"Give Me an Example Like This\": Episodic Active Reinforcement Learning from Demonstrations","created":"2024-06-05","cited_by_count":2,"area":"offlinerl"},{"id":"2508.18397","title":"Mining the Long Tail: A Comparative Study of Data-Centric Criticality Metrics for Robust Offline Reinforcement Learning in Autonomous Motion Planning","created":"2025-08-25","cited_by_count":2,"area":"offlinerl"},{"id":"2201.03834","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","created":"2022-01-11","cited_by_count":1,"area":"offlinerl"},{"id":"2410.11324","title":"Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task","created":"2024-10-15","cited_by_count":1,"area":"offlinerl"},{"id":"2505.05701","title":"Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning","created":"2025-05-09","cited_by_count":1,"area":"offlinerl"},{"id":"2511.12075","title":"Treatment Stitching with Schr\\\"odinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies","created":"2025-11-15","cited_by_count":1,"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":"2205.09550","title":"Data Valuation for Offline Reinforcement Learning","created":"2022-05-19","cited_by_count":0,"area":"offlinerl"},{"id":"2208.00478","title":"Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination","created":"2022-07-31","cited_by_count":0,"area":"offlinerl"},{"id":"2302.07741","title":"Prioritized offline Goal-swapping Experience Replay","created":"2023-02-15","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":"2502.00601","title":"Enhancing Offline Reinforcement Learning with Curriculum Learning-Based Trajectory Valuation","created":"2025-02-02","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":"2507.08707","title":"SPLASH! Sample-efficient Preference-based inverse reinforcement learning for Long-horizon Adversarial tasks from Suboptimal Hierarchical demonstrations","created":"2025-07-11","cited_by_count":0,"area":"offlinerl"},{"id":"2508.05310","title":"ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning","created":"2025-08-07","cited_by_count":0,"area":"offlinerl"},{"id":"2601.10407","title":"CS-GBA: A Critical Sample-based Gradient-guided Backdoor Attack for Offline Reinforcement Learning","created":"2026-01-15","cited_by_count":0,"area":"offlinerl"},{"id":"2608.07719","title":"CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning","created":"2026-08-07","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}