{"total":126,"rows":[{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407,"area":null},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327,"area":"offlinerl"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"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":"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":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190,"area":"offlinerl"},{"id":"2505.18719","title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","created":"2025-05-24","cited_by_count":176,"area":"vla"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154,"area":"offlinerl"},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142,"area":"mllm"},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112,"area":"offlinerl"},{"id":"2009.05990","title":"Toward the Fundamental Limits of Imitation Learning","created":"2020-09-13","cited_by_count":96,"area":"offlinerl"},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93,"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":"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":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72,"area":"offlinerl"},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"id":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66,"area":"offlinerl"},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2409.16578","title":"FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning","created":"2024-09-25","cited_by_count":54,"area":"deeprl"},{"id":"2110.03684","title":"Cross-Domain Imitation Learning via Optimal Transport","created":"2021-10-07","cited_by_count":49,"area":"offlinerl"},{"id":"2409.14674","title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","created":"2024-09-23","cited_by_count":49,"area":"offlinerl"},{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48,"area":"deeprl"},{"id":"2203.12677","title":"Vision-Based Manipulators Need to Also See from Their Hands","created":"2022-03-15","cited_by_count":47,"area":null},{"id":"2111.07999","title":"Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization","created":"2021-11-15","cited_by_count":46,"area":null},{"id":"2503.24361","title":"Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation","created":"2025-03-31","cited_by_count":46,"area":null},{"id":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45,"area":"offlinerl"},{"id":"2402.17768","title":"Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning","created":"2024-02-27","cited_by_count":35,"area":"offlinerl"},{"id":"2210.07442","title":"Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds","created":"2022-10-14","cited_by_count":32,"area":null},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31,"area":"offlinerl"},{"id":"2403.12203","title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","created":"2024-03-18","cited_by_count":31,"area":"deeprl"},{"id":"2008.09167","title":"Imitation Learning with Sinkhorn Distances","created":"2020-08-20","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":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"id":"2310.16014","title":"Human-in-the-Loop Task and Motion Planning for Imitation Learning","created":"2023-10-24","cited_by_count":29,"area":"offlinerl"},{"id":"2106.09422","title":"CRIL: Continual Robot Imitation Learning via Generative and Prediction Model","created":"2021-06-17","cited_by_count":24,"area":"offlinerl"},{"id":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24,"area":null},{"id":"2012.06899","title":"Semi-supervised reward learning for offline reinforcement learning","created":"2020-12-12","cited_by_count":23,"area":"alignment"},{"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":"2103.17118","title":"iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving","created":"2021-03-31","cited_by_count":21,"area":"driving"},{"id":"2310.12077","title":"One-Shot Imitation Learning: A Pose Estimation Perspective","created":"2023-10-18","cited_by_count":21,"area":"offlinerl"},{"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":"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":"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":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","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":"2407.12448","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","created":"2024-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2512.01061","title":"Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer","created":"2025-11-30","cited_by_count":15,"area":null},{"id":"1904.01139","title":"Generative predecessor models for sample-efficient imitation learning","created":"2019-04-01","cited_by_count":14,"area":"offlinerl"},{"id":"2306.12860","title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","created":"2023-06-22","cited_by_count":14,"area":null},{"id":"2404.18926","title":"Point Cloud Models Improve Visual Robustness in Robotic Learners","created":"2024-04-29","cited_by_count":14,"area":null},{"id":"2107.09046","title":"Playful Interactions for Representation Learning","created":"2021-07-19","cited_by_count":13,"area":"offlinerl"},{"id":"2405.03379","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","created":"2024-05-06","cited_by_count":13,"area":"deeprl"},{"id":"2506.03863","title":"STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2209.12072","title":"Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skills","created":"2022-09-24","cited_by_count":12,"area":"driving"},{"id":"1803.01129","title":"OIL: Observational Imitation Learning","created":"2018-03-03","cited_by_count":11,"area":"offlinerl"},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2306.06799","title":"On the Efficacy of 3D Point Cloud Reinforcement Learning","created":"2023-06-11","cited_by_count":11,"area":null},{"id":"2204.09597","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","created":"2022-03-20","cited_by_count":10,"area":null},{"id":"2502.20168","title":"Accelerating Model-Based Reinforcement Learning with State-Space World Models","created":"2025-02-27","cited_by_count":10,"area":"wm"},{"id":"1902.10657","title":"From explanation to synthesis: Compositional program induction for learning from demonstration","created":"2019-02-27","cited_by_count":9,"area":"offlinerl"},{"id":"2007.11646","title":"Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks","created":"2020-07-22","cited_by_count":9,"area":"offlinerl"},{"id":"2208.12986","title":"6D Robotic Assembly Based on RGB-only Object Pose Estimation","created":"2022-08-27","cited_by_count":9,"area":null},{"id":"2310.17303","title":"Demonstration-Regularized RL","created":"2023-10-26","cited_by_count":9,"area":"alignment"},{"id":"2602.12628","title":"Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models","created":"2026-02-13","cited_by_count":9,"area":"vla"},{"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":"2201.11981","title":"Transfering Hierarchical Structure with Dual Meta Imitation Learning","created":"2022-01-28","cited_by_count":7,"area":"offlinerl"},{"id":"2210.09337","title":"Robust Imitation of a Few Demonstrations with a Backwards Model","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2104.00442","title":"Touch-based Curiosity for Sparse-Reward Tasks","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2210.11201","title":"Robust Imitation via Mirror Descent Inverse Reinforcement Learning","created":"2022-10-20","cited_by_count":6,"area":"offlinerl"},{"id":"2306.15858","title":"Hierarchical Graph Neural Networks for Proprioceptive 6D Pose Estimation of In-hand Objects","created":"2023-06-28","cited_by_count":6,"area":null},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2508.01943","title":"ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks","created":"2025-08-03","cited_by_count":6,"area":"lr"},{"id":"2503.14259","title":"Quantization-Free Autoregressive Action Transformer","created":"2025-03-18","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":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4,"area":"offlinerl"},{"id":"2410.06151","title":"Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity","created":"2024-10-08","cited_by_count":4,"area":"offlinerl"},{"id":"2410.15910","title":"Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning","created":"2024-10-21","cited_by_count":4,"area":"offlinerl"},{"id":"2411.06965","title":"Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration","created":"2024-11-11","cited_by_count":4,"area":"offlinerl"},{"id":"1903.07854","title":"Hindsight Generative Adversarial Imitation Learning","created":"2019-03-19","cited_by_count":3,"area":"offlinerl"},{"id":"2101.00186","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","created":"2021-01-01","cited_by_count":3,"area":"offlinerl"},{"id":"2101.04736","title":"Bootstrapping Motor Skill Learning with Motion Planning","created":"2021-01-12","cited_by_count":3,"area":null},{"id":"2206.11299","title":"Latent Policies for Adversarial Imitation Learning","created":"2022-06-22","cited_by_count":3,"area":"offlinerl"},{"id":"2210.01379","title":"Extraneousness-Aware Imitation Learning","created":"2022-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2309.14003","title":"Hierarchical Imitation Learning for Stochastic Environments","created":"2023-09-25","cited_by_count":3,"area":"offlinerl"},{"id":"2402.09387","title":"Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning","created":"2024-02-14","cited_by_count":3,"area":null},{"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":"2605.09989","title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","created":"2026-05-11","cited_by_count":3,"area":"offlinerl"},{"id":"2008.01913","title":"Generalization Guarantees for Imitation Learning","created":"2020-08-05","cited_by_count":2,"area":"offlinerl"},{"id":"2104.14386","title":"Pre-training of Deep RL Agents for Improved Learning under Domain Randomization","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2202.06027","title":"End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation","created":"2022-02-12","cited_by_count":2,"area":null}],"next_cursor":"100"}