{"total":86,"rows":[{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"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":"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":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"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":"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":"2305.10282","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","created":"2023-05-17","cited_by_count":16,"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":"2309.09408","title":"Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration","created":"2023-09-18","cited_by_count":14,"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":"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":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2408.08441","title":"D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning","created":"2024-08-15","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":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2601.07821","title":"Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation","created":"2026-01-12","cited_by_count":11,"area":"offlinerl"},{"id":"2306.05726","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","created":"2023-06-09","cited_by_count":10,"area":"offlinerl"},{"id":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"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":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","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":"2312.09844","title":"Small Dataset, Big Gains: Enhancing Reinforcement Learning by Offline Pre-Training with Model Based Augmentation","created":"2023-12-15","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":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","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":"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":"2506.18847","title":"Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning","created":"2025-06-23","cited_by_count":5,"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":"2410.07933","title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization","created":"2024-10-10","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":"2603.05504","title":"RoboPocket: Improve Robot Policies Instantly with Your Phone","created":"2026-03-05","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":"2605.27079","title":"Trust Region Q Adjoint Matching","created":"2026-05-26","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":"2509.24748","title":"Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption","created":"2025-09-29","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":"2605.05172","title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","created":"2026-05-06","cited_by_count":3,"area":"offlinerl"},{"id":"2410.14957","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","created":"2024-10-19","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":"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":"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":"2506.00131","title":"Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization","created":"2025-05-30","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":"2512.06692","title":"State Diversity Matters in Offline Behavior Distillation","created":"2025-12-07","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":"2601.08731","title":"Learning from Demonstrations via Capability-Aware Goal Sampling","created":"2026-01-13","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":"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":"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":"2512.18246","title":"Offline Behavioral Data Selection","created":"2025-12-20","cited_by_count":0,"area":"offlinerl"},{"id":"2601.15761","title":"Off-Policy Actor-Critic with Sigmoid-Bounded Entropy for Real-World Robot Learning","created":"2026-01-22","cited_by_count":0,"area":"offlinerl"},{"id":"2602.00629","title":"Action-Free Offline-to-Online RL via Discretised State Policies","created":"2026-01-31","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":"2603.18326","title":"Escaping Offline Pessimism: Vector-Field Reward Shaping for Safe Frontier Exploration","created":"2026-03-18","cited_by_count":0,"area":"offlinerl"},{"id":"2604.13966","title":"Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation","created":"2026-04-15","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":"2605.28372","title":"Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learning","created":"2026-05-27","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":"2608.10473","title":"Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning","created":"2026-08-11","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":"2608.28878","title":"Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management","created":"2026-08-28","cited_by_count":0,"area":"offlinerl"},{"id":"2609.06667","title":"Behavioral Cloning Outperforms Entropy-Regularized RL: Critic-Driven Failure of Actor-Critic Methods on Adaptive Tumor Treatment","created":"2026-09-06","cited_by_count":0,"area":"offlinerl"},{"id":"2609.12749","title":"SCQ: Stabilizing Conservative Q-Learning with Sigmoid-Bounded Entropy","created":"2026-09-11","cited_by_count":0,"area":"offlinerl"},{"id":"2609.33127","title":"Policy Plasticity Matters in Offline-to-Online Reinforcement Learning: Refitting Offline Policies for Online Adaptation","created":"2026-09-27","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}