{"total":98,"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":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144,"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":"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":"2311.02198","title":"Imitation Bootstrapped Reinforcement Learning","created":"2023-11-03","cited_by_count":64,"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":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2402.08848","title":"Hybrid Inverse Reinforcement Learning","created":"2024-02-13","cited_by_count":32,"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":"2310.04411","title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","created":"2023-10-06","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":"2407.00699","title":"Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning","created":"2024-06-30","cited_by_count":17,"area":"offlinerl"},{"id":"2506.05294","title":"A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search","created":"2025-06-05","cited_by_count":17,"area":"offlinerl"},{"id":"2309.03322","title":"REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation","created":"2023-09-06","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":"2506.13762","title":"Touch begins where vision ends: Generalizable policies for contact-rich manipulation","created":"2025-06-16","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":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","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":"2502.13519","title":"MILE: Model-based Intervention Learning","created":"2025-02-19","cited_by_count":10,"area":"offlinerl"},{"id":"2407.20164","title":"Language-Conditioned Offline RL for Multi-Robot Navigation","created":"2024-07-29","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":"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":"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":"2402.02017","title":"Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning","created":"2024-02-03","cited_by_count":7,"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":"2408.04054","title":"PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning","created":"2024-08-07","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":"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":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","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":"2304.12886","title":"What can online reinforcement learning with function approximation benefit from general coverage conditions?","created":"2023-04-25","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":"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":"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":"2501.02330","title":"SR-Reward: Taking The Path More Traveled","created":"2025-01-04","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":"2605.12236","title":"TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning","created":"2026-05-12","cited_by_count":3,"area":"offlinerl"},{"id":"2304.00977","title":"Selective Reincarnation: Offline-to-Online Multi-Agent Reinforcement Learning","created":"2023-03-31","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":"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":"2503.03056","title":"A2Perf: Real-World Autonomous Agents Benchmark","created":"2025-03-04","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":"2605.11151","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":"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":"2508.19900","title":"Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning","created":"2025-08-27","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":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","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":"2604.07072","title":"Epistemic Robust Offline Reinforcement Learning","created":"2026-04-08","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":"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":"2606.09381","title":"ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration","created":"2026-06-08","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":"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":"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":"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":"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":"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":"2605.13401","title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","created":"2026-05-13","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":"2606.21085","title":"Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition","created":"2026-06-19","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":"2608.12063","title":"Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL","created":"2026-08-12","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":"2609.06667","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":"2609.13234","title":"Harnessing human expertise for high-precision robotic assembly in industrialized construction: A sample-efficient installer-in-the-loop interactive reinforcement learning framework","created":"2026-09-02","cited_by_count":0,"area":"offlinerl"},{"id":"2609.30023","title":"Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation","created":"2026-09-24","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"}],"next_cursor":null}