{"total":18,"rows":[{"id":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","cited_by_count":26,"area":"offlinerl"},{"id":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17,"area":"offlinerl"},{"id":"2405.19909","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","created":"2024-05-30","cited_by_count":13,"area":"offlinerl"},{"id":"2403.07262","title":"A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective","created":"2024-03-12","cited_by_count":11,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2409.10589","title":"Offline Reinforcement Learning for Learning to Dispatch for Job Shop Scheduling","created":"2024-09-16","cited_by_count":6,"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":"2411.06601","title":"OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Control","created":"2024-11-10","cited_by_count":3,"area":"offlinerl"},{"id":"2506.08417","title":"Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood","created":"2025-06-10","cited_by_count":3,"area":"offlinerl"},{"id":"2605.11151","title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","created":"2026-05-11","cited_by_count":2,"area":"offlinerl"},{"id":"2403.00841","title":"Offline Fictitious Self-Play for Competitive Games","created":"2024-02-29","cited_by_count":1,"area":"offlinerl"},{"id":"2406.09486","title":"SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets","created":"2024-06-13","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":"2506.14058","title":"Implicit Constraint-Aware Off-Policy Correction for Offline Reinforcement Learning","created":"2025-06-16","cited_by_count":1,"area":"offlinerl"},{"id":"2506.02577","title":"Reachability Weighted Offline Goal-conditioned Resampling","created":"2025-06-03","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":"2507.06701","title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement","created":"2025-07-09","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}