{"total":340,"rows":[{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395,"area":"offlinerl"},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"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":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158,"area":null},{"id":"2502.05450","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","created":"2025-02-08","cited_by_count":154,"area":"vla"},{"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":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"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":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"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":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90,"area":null},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89,"area":null},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89,"area":"offlinerl"},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85,"area":null},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78,"area":null},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77,"area":"offlinerl"},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75,"area":"offlinerl"},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72,"area":"offlinerl"},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72,"area":null},{"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":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"area":"offlinerl"},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2402.05808","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","created":"2024-02-08","cited_by_count":65,"area":"lr"},{"id":"2311.02198","title":"Imitation Bootstrapped Reinforcement Learning","created":"2023-11-03","cited_by_count":64,"area":"offlinerl"},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55,"area":null},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"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":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49,"area":null},{"id":"2210.05492","title":"Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning","created":"2022-10-11","cited_by_count":48,"area":null},{"id":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43,"area":"offlinerl"},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"1810.11748","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","created":"2018-10-28","cited_by_count":41,"area":"alignment"},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"1805.11240","title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","created":"2018-05-29","cited_by_count":39,"area":"offlinerl"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2305.04412","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","created":"2023-05-08","cited_by_count":36,"area":"driving"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34,"area":null},{"id":"2210.12631","title":"LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation","created":"2022-10-23","cited_by_count":34,"area":null},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2209.10579","title":"First-order Policy Optimization for Robust Markov Decision Process","created":"2022-09-21","cited_by_count":32,"area":null},{"id":"2401.03160","title":"HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving","created":"2024-01-06","cited_by_count":32,"area":"driving"},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31,"area":"offlinerl"},{"id":"2108.13035","title":"SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning","created":"2021-08-30","cited_by_count":31,"area":null},{"id":"1904.06317","title":"Few-Shot Bayesian Imitation Learning with Logical Program Policies","created":"2019-04-12","cited_by_count":30,"area":"offlinerl"},{"id":"2103.11512","title":"Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study","created":"2021-03-21","cited_by_count":30,"area":null},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"area":"offlinerl"},{"id":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"1906.03352","title":"Watch, Try, Learn: Meta-Learning from Demonstrations and Reward","created":"2019-06-07","cited_by_count":28,"area":"offlinerl"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2303.13002","title":"Planning Goals for Exploration","created":"2023-03-23","cited_by_count":28,"area":null},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2103.13834","title":"Self-Imitation Learning by Planning","created":"2021-03-25","cited_by_count":26,"area":"offlinerl"},{"id":"1912.12204","title":"Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data","created":"2019-12-24","cited_by_count":24,"area":"offlinerl"},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2307.07871","title":"The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents","created":"2023-07-15","cited_by_count":24,"area":"agents"},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2302.09772","title":"Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot","created":"2023-02-20","cited_by_count":23,"area":null},{"id":"2109.12516","title":"Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving","created":"2021-09-26","cited_by_count":22,"area":"driving"},{"id":"2205.05212","title":"A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning","created":"2022-05-11","cited_by_count":22,"area":null},{"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":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2502.20382","title":"Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization","created":"2025-02-27","cited_by_count":21,"area":null},{"id":"2210.09598","title":"Planning for Sample Efficient Imitation Learning","created":"2022-10-18","cited_by_count":20,"area":"offlinerl"},{"id":"2211.10936","title":"Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling","created":"2022-11-20","cited_by_count":20,"area":null},{"id":"2211.11802","title":"Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning","created":"2022-11-21","cited_by_count":20,"area":null},{"id":"2310.06147","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","created":"2023-10-09","cited_by_count":20,"area":"alignment"},{"id":"2404.19409","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","created":"2024-04-30","cited_by_count":20,"area":"alignment"},{"id":"2207.10148","title":"Learning Deformable Object Manipulation from Expert Demonstrations","created":"2022-07-20","cited_by_count":19,"area":"offlinerl"},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"1803.05402","title":"Imitation Learning with Concurrent Actions in 3D Games","created":"2018-03-14","cited_by_count":18,"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":"2102.09754","title":"VisuoSpatial Foresight for Physical Sequential Fabric Manipulation","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2212.07407","title":"Cross-Domain Transfer via Semantic Skill Imitation","created":"2022-12-14","cited_by_count":18,"area":null},{"id":"2309.10175","title":"One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers","created":"2023-09-18","cited_by_count":17,"area":"offlinerl"},{"id":"2405.02425","title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":17,"area":"deeprl"},{"id":"2104.07246","title":"Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving","created":"2021-04-15","cited_by_count":16,"area":"driving"},{"id":"2205.15460","title":"Critic Sequential Monte Carlo","created":"2022-05-30","cited_by_count":16,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"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":"2510.24108","title":"Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer","created":"2025-10-28","cited_by_count":16,"area":"driving"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2109.04307","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","created":"2021-09-09","cited_by_count":15,"area":"offlinerl"},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"}],"next_cursor":"100"}