{"total":93,"rows":[{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"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":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214,"area":"offlinerl"},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206,"area":"offlinerl"},{"id":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204,"area":"offlinerl"},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126,"area":"offlinerl"},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"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":"2105.06411","title":"Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration","created":"2021-05-13","cited_by_count":93,"area":"offlinerl"},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91,"area":"offlinerl"},{"id":"2204.12490","title":"From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation","created":"2022-04-26","cited_by_count":82,"area":"offlinerl"},{"id":"2203.13251","title":"Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation","created":"2022-03-24","cited_by_count":78,"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":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72,"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":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51,"area":"offlinerl"},{"id":"2112.07544","title":"Modeling Strong and Human-Like Gameplay with KL-Regularized Search","created":"2021-12-14","cited_by_count":50,"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":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45,"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":"1805.11240","title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","created":"2018-05-29","cited_by_count":39,"area":"offlinerl"},{"id":"2110.04276","title":"Offline Meta-Reinforcement Learning for Industrial Insertion","created":"2021-10-08","cited_by_count":39,"area":"offlinerl"},{"id":"2204.02863","title":"Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation Learning","created":"2022-04-06","cited_by_count":38,"area":"offlinerl"},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31,"area":"offlinerl"},{"id":"2111.02767","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","created":"2021-11-04","cited_by_count":31,"area":"offlinerl"},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"area":"offlinerl"},{"id":"2008.07682","title":"Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation","created":"2020-08-18","cited_by_count":28,"area":"offlinerl"},{"id":"2103.13834","title":"Self-Imitation Learning by Planning","created":"2021-03-25","cited_by_count":26,"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":"2205.14850","title":"Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning","created":"2022-05-30","cited_by_count":22,"area":"offlinerl"},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2111.07447","title":"Learning Multi-Stage Tasks with One Demonstration via Self-Replay","created":"2021-11-14","cited_by_count":21,"area":"offlinerl"},{"id":"2111.08857","title":"SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition","created":"2021-11-17","cited_by_count":20,"area":"offlinerl"},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18,"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":"1904.01139","title":"Generative predecessor models for sample-efficient imitation learning","created":"2019-04-01","cited_by_count":14,"area":"offlinerl"},{"id":"2506.13498","title":"A Survey on Imitation Learning for Contact-Rich Tasks in Robotics","created":"2025-06-16","cited_by_count":14,"area":"offlinerl"},{"id":"2209.15073","title":"A Benchmark Comparison of Imitation Learning-based Control Policies for Autonomous Racing","created":"2022-09-29","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":"2410.18065","title":"SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation","created":"2024-10-23","cited_by_count":11,"area":"offlinerl"},{"id":"2011.13467","title":"Episodic Self-Imitation Learning with Hindsight","created":"2020-11-26","cited_by_count":10,"area":"offlinerl"},{"id":"2111.06383","title":"Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation","created":"2021-11-11","cited_by_count":10,"area":"offlinerl"},{"id":"2301.00051","title":"Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks","created":"2022-12-30","cited_by_count":10,"area":"offlinerl"},{"id":"2304.03833","title":"Learning Robot Manipulation from Cross-Morphology Demonstration","created":"2023-04-07","cited_by_count":8,"area":"offlinerl"},{"id":"1907.02140","title":"Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model","created":"2019-07-03","cited_by_count":7,"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":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","cited_by_count":6,"area":"offlinerl"},{"id":"1910.01738","title":"State Representation Learning from Demonstration","created":"2019-09-15","cited_by_count":5,"area":"offlinerl"},{"id":"1910.12154","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","created":"2019-10-26","cited_by_count":5,"area":"offlinerl"},{"id":"2012.13682","title":"POPO: Pessimistic Offline Policy Optimization","created":"2020-12-26","cited_by_count":5,"area":"offlinerl"},{"id":"2106.09159","title":"Automatic Curricula via Expert Demonstrations","created":"2021-06-16","cited_by_count":5,"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":"2110.14464","title":"Learning from demonstrations with SACR2: Soft Actor-Critic with Reward Relabeling","created":"2021-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4,"area":"offlinerl"},{"id":"2306.06754","title":"Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning","created":"2023-06-11","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":"2605.27079","title":"Trust Region Q Adjoint Matching","created":"2026-05-26","cited_by_count":4,"area":"offlinerl"},{"id":"2211.16838","title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation","created":"2022-11-30","cited_by_count":3,"area":"offlinerl"},{"id":"2405.09760","title":"Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning","created":"2024-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2411.10268","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","created":"2024-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2210.10999","title":"Task Phasing: Automated Curriculum Learning from Demonstrations","created":"2022-10-20","cited_by_count":2,"area":"offlinerl"},{"id":"2406.03069","title":"\"Give Me an Example Like This\": Episodic Active Reinforcement Learning from Demonstrations","created":"2024-06-05","cited_by_count":2,"area":"offlinerl"},{"id":"2504.05585","title":"TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning","created":"2025-04-08","cited_by_count":2,"area":"offlinerl"},{"id":"2201.03834","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","created":"2022-01-11","cited_by_count":1,"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":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2509.26605","title":"Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning","created":"2025-09-30","cited_by_count":1,"area":"offlinerl"},{"id":"2107.11811","title":"Reinforced Imitation Learning by Free Energy Principle","created":"2021-07-25","cited_by_count":0,"area":"offlinerl"},{"id":"2109.07380","title":"DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning","created":"2021-09-15","cited_by_count":0,"area":"offlinerl"},{"id":"2110.10905","title":"Efficient Robotic Manipulation Through Offline-to-Online Reinforcement Learning and Goal-Aware State Information","created":"2021-10-21","cited_by_count":0,"area":"offlinerl"},{"id":"2111.08156","title":"Improving Learning from Demonstrations by Learning from Experience","created":"2021-11-16","cited_by_count":0,"area":"offlinerl"},{"id":"2202.11325","title":"Reinforcement Learning from Demonstrations by Novel Interactive Expert and Application to Automatic Berthing Control Systems for Unmanned Surface Vessel","created":"2022-02-23","cited_by_count":0,"area":"offlinerl"},{"id":"2208.00478","title":"Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination","created":"2022-07-31","cited_by_count":0,"area":"offlinerl"},{"id":"2210.07015","title":"Augmentation for Learning From Demonstration with Environmental Constraints","created":"2022-10-13","cited_by_count":0,"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":"2402.09355","title":"Single-Reset Divide & Conquer Imitation Learning","created":"2024-02-14","cited_by_count":0,"area":"offlinerl"},{"id":"2403.01059","title":"Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)","created":"2024-03-02","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":"2509.03206","title":"Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback","created":"2025-09-03","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":"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":"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":"2609.03590","title":"From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control","created":"2026-09-03","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"}],"next_cursor":null}