{"total":68,"rows":[{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"area":"offlinerl"},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2505.08078","title":"What Matters for Batch Online Reinforcement Learning in Robotics?","created":"2025-05-12","cited_by_count":15,"area":"offlinerl"},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","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":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"2606.11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","created":"2026-06-09","cited_by_count":6,"area":"offlinerl"},{"id":"2306.08772","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19923","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","created":"2025-05-26","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":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4,"area":"offlinerl"},{"id":"2406.06309","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","created":"2024-06-10","cited_by_count":4,"area":"offlinerl"},{"id":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2510.01460","title":"The Three Regimes of Offline-to-Online Reinforcement Learning","created":"2025-10-01","cited_by_count":4,"area":"offlinerl"},{"id":"2602.05051","title":"ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation","created":"2026-02-04","cited_by_count":4,"area":"offlinerl"},{"id":"2606.00350","title":"Drift Q-Learning","created":"2026-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2404.16399","title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","created":"2024-04-25","cited_by_count":3,"area":"offlinerl"},{"id":"2408.02165","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","created":"2024-08-04","cited_by_count":3,"area":"offlinerl"},{"id":"2603.13971","title":"Chunk-Guided Q-Learning","created":"2026-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2409.02724","title":"Surgical Task Automation Using Actor-Critic Frameworks and Self-Supervised Imitation Learning","created":"2024-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2409.07606","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","created":"2024-09-11","cited_by_count":2,"area":"offlinerl"},{"id":"2511.02567","title":"Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning","created":"2025-11-04","cited_by_count":2,"area":"offlinerl"},{"id":"2603.08399","title":"A Recipe for Stable Offline Multi-agent Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"offlinerl"},{"id":"2605.01663","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","created":"2026-05-03","cited_by_count":2,"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":"2605.15603","title":"Offline Reinforcement Learning with Universal Horizon Models","created":"2026-05-15","cited_by_count":2,"area":"offlinerl"},{"id":"2605.22711","title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-21","cited_by_count":2,"area":"offlinerl"},{"id":"2406.04534","title":"Strategically Conservative Q-Learning","created":"2024-06-06","cited_by_count":1,"area":"offlinerl"},{"id":"2408.10713","title":"Offline Model-Based Reinforcement Learning with Anti-Exploration","created":"2024-08-20","cited_by_count":1,"area":"offlinerl"},{"id":"2501.18138","title":"B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning","created":"2025-01-30","cited_by_count":1,"area":"offlinerl"},{"id":"2506.00131","title":"Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization","created":"2025-05-30","cited_by_count":1,"area":"offlinerl"},{"id":"2507.10843","title":"Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps","created":"2025-07-14","cited_by_count":1,"area":"offlinerl"},{"id":"2508.19900","title":"Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning","created":"2025-08-27","cited_by_count":1,"area":"offlinerl"},{"id":"2509.24067","title":"In-Context Compositional Q-Learning for Offline Reinforcement Learning","created":"2025-09-28","cited_by_count":1,"area":"offlinerl"},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2512.06692","title":"State Diversity Matters in Offline Behavior Distillation","created":"2025-12-07","cited_by_count":1,"area":"offlinerl"},{"id":"2602.07441","title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","created":"2026-02-07","cited_by_count":1,"area":"offlinerl"},{"id":"2605.01968","title":"AdamO: A Collapse-Suppressed Optimizer for Offline RL","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2406.13376","title":"Efficient Offline Reinforcement Learning: First Imitate, then Improve","created":"2024-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2508.04225","title":"Symmetric Behavior Regularized Policy Optimization","created":"2025-08-06","cited_by_count":0,"area":"offlinerl"},{"id":"2508.05960","title":"Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning","created":"2025-08-08","cited_by_count":0,"area":"offlinerl"},{"id":"2509.10303","title":"Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions","created":"2025-09-12","cited_by_count":0,"area":"offlinerl"},{"id":"2510.02695","title":"RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2512.00536","title":"Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets","created":"2025-11-29","cited_by_count":0,"area":"offlinerl"},{"id":"2601.00452","title":"Imitation from Observations with Trajectory-Level Generative Embeddings","created":"2026-01-01","cited_by_count":0,"area":"offlinerl"},{"id":"2601.18107","title":"Beyond Static Datasets: Robust Offline Policy Optimization via Vetted Synthetic Transitions","created":"2026-01-26","cited_by_count":0,"area":"offlinerl"},{"id":"2605.11009","title":"ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"},{"id":"2605.13401","title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2605.14779","title":"Peng's Q($\\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning","created":"2026-05-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.24152","title":"Neuro-Inspired Inverse Learning for Planning and Control","created":"2026-05-22","cited_by_count":0,"area":"offlinerl"},{"id":"2605.29033","title":"Moment Matching Q-Learning","created":"2026-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2608.23939","title":"CoDrift: Compositional Drifting for Offline Reinforcement Learning","created":"2026-08-25","cited_by_count":0,"area":"offlinerl"},{"id":"2609.13730","title":"JumpStart Your Policy Learning with Lessons from 160,000 Training Runs","created":"2026-09-12","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":"2609.33259","title":"GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences","created":"2026-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2609.40149","title":"Role-Adaptive Policy Optimization for Offline Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2610.16984","title":"From Suboptimal to Optimal: One-Step Latent Flow Policies for Offline Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"offlinerl"},{"id":"2610.20190","title":"Value-Guided Repulsion for Offline Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}