{"total":100,"rows":[{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104,"area":"offlinerl"},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78,"area":"offlinerl"},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"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":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61,"area":"offlinerl"},{"id":"2306.14744","title":"ChiPFormer: Transferable Chip Placement via Offline Decision Transformer","created":"2023-06-26","cited_by_count":42,"area":"offlinerl"},{"id":"2303.07693","title":"Adaptive Policy Learning for Offline-to-Online Reinforcement Learning","created":"2023-03-14","cited_by_count":40,"area":"offlinerl"},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37,"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":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"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":"2303.17396","title":"Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions","created":"2023-03-30","cited_by_count":26,"area":"offlinerl"},{"id":"2310.17966","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","created":"2023-10-27","cited_by_count":26,"area":"offlinerl"},{"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":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2306.06871","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","created":"2023-06-12","cited_by_count":20,"area":"offlinerl"},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17,"area":"offlinerl"},{"id":"2312.07685","title":"A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning","created":"2023-12-12","cited_by_count":15,"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":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2506.07505","title":"Reinforcement Learning via Implicit Imitation Guidance","created":"2025-06-09","cited_by_count":12,"area":"offlinerl"},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11,"area":"offlinerl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","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":"2205.03353","title":"How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation","created":"2022-05-06","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":"2508.06806","title":"Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation","created":"2025-08-09","cited_by_count":9,"area":"offlinerl"},{"id":"2306.07541","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","created":"2023-06-13","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":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2310.08558","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","created":"2023-10-12","cited_by_count":7,"area":"offlinerl"},{"id":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"2401.05899","title":"Optimistic Model Rollouts for Pessimistic Offline Policy Optimization","created":"2024-01-11","cited_by_count":6,"area":"offlinerl"},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","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":"2502.08259","title":"Balancing optimism and pessimism in offline-to-online learning","created":"2025-02-12","cited_by_count":6,"area":"offlinerl"},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","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":"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":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2310.05723","title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":"offlinerl"},{"id":"2503.12222","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning","created":"2025-03-15","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":"2605.10044","title":"Adaptive Action Chunking via Multi-Chunk Q Value Estimation","created":"2026-05-11","cited_by_count":4,"area":"offlinerl"},{"id":"2410.19450","title":"Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration","created":"2024-10-25","cited_by_count":3,"area":"offlinerl"},{"id":"2501.14199","title":"Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework","created":"2025-01-24","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":"2512.23694","title":"Bellman Calibration for $V$-Learning in Offline Reinforcement Learning","created":"2025-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2209.06579","title":"C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learning","created":"2022-09-14","cited_by_count":2,"area":"offlinerl"},{"id":"2302.14833","title":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":2,"area":"offlinerl"},{"id":"2406.08238","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","created":"2024-06-12","cited_by_count":2,"area":"offlinerl"},{"id":"2412.14834","title":"Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning","created":"2024-12-19","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":"2605.11151","title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","created":"2026-05-11","cited_by_count":2,"area":"offlinerl"},{"id":"2212.03562","title":"Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble","created":"2022-12-07","cited_by_count":1,"area":"offlinerl"},{"id":"2310.02405","title":"PCGPT: Procedural Content Generation via Transformers","created":"2023-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2405.07223","title":"Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning","created":"2024-05-12","cited_by_count":1,"area":"offlinerl"},{"id":"2406.04534","title":"Strategically Conservative Q-Learning","created":"2024-06-06","cited_by_count":1,"area":"offlinerl"},{"id":"2407.09415","title":"A Benchmark Environment for Offline Reinforcement Learning in Racing Games","created":"2024-07-12","cited_by_count":1,"area":"offlinerl"},{"id":"2412.18781","title":"Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations","created":"2024-12-25","cited_by_count":1,"area":"offlinerl"},{"id":"2502.11480","title":"Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective","created":"2025-02-17","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":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2511.03695","title":"Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL","created":"2025-11-05","cited_by_count":1,"area":"offlinerl"},{"id":"2601.00167","title":"Online Finetuning Decision Transformers with Pure RL Gradients","created":"2026-01-01","cited_by_count":1,"area":"offlinerl"},{"id":"2605.05123","title":"Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning","created":"2026-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2605.05544","title":"Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning","created":"2026-05-07","cited_by_count":1,"area":"offlinerl"},{"id":"2310.19805","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","created":"2023-10-07","cited_by_count":0,"area":"offlinerl"},{"id":"2410.18626","title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","created":"2024-10-24","cited_by_count":0,"area":"offlinerl"},{"id":"2410.23737","title":"A Non-Monolithic Policy Approach of Offline-to-Online Reinforcement Learning","created":"2024-10-31","cited_by_count":0,"area":"offlinerl"},{"id":"2412.05675","title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","created":"2024-12-07","cited_by_count":0,"area":"offlinerl"},{"id":"2510.00466","title":"Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social Navigation","created":"2025-10-01","cited_by_count":0,"area":"offlinerl"},{"id":"2510.13358","title":"Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control","created":"2025-10-15","cited_by_count":0,"area":"offlinerl"},{"id":"2511.03828","title":"From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning","created":"2025-11-05","cited_by_count":0,"area":"offlinerl"},{"id":"2512.00383","title":"An Empirical Study on the Effectiveness of Incorporating Offline RL As Online RL Subroutines","created":"2025-11-29","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":"2603.09378","title":"SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space","created":"2026-03-10","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":"2605.14497","title":"ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization","created":"2026-05-14","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":"2605.18675","title":"COOPO: Cyclic Offline-Online Policy Optimization Algorithm","created":"2026-05-18","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":"2605.29405","title":"Information-Directed Offline-to-Online Reinforcement Learning","created":"2026-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2607.09866","title":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning","created":"2026-07-10","cited_by_count":0,"area":"offlinerl"},{"id":"2608.22284","title":"Learning from the Test: Self-Referential Differential Testing for Deep RL Agents","created":"2026-08-23","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2609.39868","title":"Completion-Aware Cross-Fidelity Offline-to-Online Reinforcement Learning for Multi-Line Bus Holding","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}