{"total":319,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548,"area":"agents"},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511,"area":null},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508,"area":"wm"},{"id":"2506.07339","title":"Real-Time Execution of Action Chunking Flow Policies","created":"2025-06-09","cited_by_count":216,"area":null},{"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":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187,"area":null},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168,"area":null},{"id":"2211.07638","title":"Legged Locomotion in Challenging Terrains using Egocentric Vision","created":"2022-11-14","cited_by_count":151,"area":null},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149,"area":null},{"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":"2502.01143","title":"ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills","created":"2025-02-03","cited_by_count":130,"area":null},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101,"area":null},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"area":null},{"id":"2208.07860","title":"A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning","created":"2022-08-16","cited_by_count":83,"area":"wm"},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83,"area":null},{"id":"2307.03659","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","created":"2023-07-07","cited_by_count":82,"area":"offlinerl"},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2107.03996","title":"Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers","created":"2021-07-08","cited_by_count":79,"area":null},{"id":"2111.01674","title":"Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots","created":"2021-10-25","cited_by_count":76,"area":null},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"area":null},{"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":"2408.14472","title":"Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning","created":"2024-08-26","cited_by_count":56,"area":"wm"},{"id":"2104.04644","title":"Fast and Efficient Locomotion via Learned Gait Transitions","created":"2021-04-09","cited_by_count":54,"area":null},{"id":"2404.05695","title":"Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer","created":"2024-04-08","cited_by_count":53,"area":null},{"id":"2107.00646","title":"Learning to See before Learning to Act: Visual Pre-training for Manipulation","created":"2021-07-01","cited_by_count":51,"area":null},{"id":"2112.02094","title":"Coupling Vision and Proprioception for Navigation of Legged Robots","created":"2021-12-03","cited_by_count":51,"area":null},{"id":"2501.10100","title":"Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics","created":"2025-01-17","cited_by_count":51,"area":"wm"},{"id":"2503.19901","title":"TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization","created":"2025-03-25","cited_by_count":51,"area":null},{"id":"2104.07662","title":"Auto-Tuned Sim-to-Real Transfer","created":"2021-04-15","cited_by_count":49,"area":null},{"id":"2209.05309","title":"GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots","created":"2022-09-12","cited_by_count":48,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2110.15344","title":"Learning to Jump from Pixels","created":"2021-10-28","cited_by_count":45,"area":null},{"id":"2309.09969","title":"Prompt a Robot to Walk with Large Language Models","created":"2023-09-18","cited_by_count":45,"area":null},{"id":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44,"area":null},{"id":"2305.14654","title":"Barkour: Benchmarking Animal-level Agility with Quadruped Robots","created":"2023-05-24","cited_by_count":41,"area":null},{"id":"2304.01159","title":"DribbleBot: Dynamic Legged Manipulation in the Wild","created":"2023-04-03","cited_by_count":40,"area":null},{"id":"2312.11460","title":"Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response","created":"2023-12-18","cited_by_count":39,"area":null},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37,"area":null},{"id":"2308.15143","title":"Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models","created":"2023-08-29","cited_by_count":37,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2211.00458","title":"CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion","created":"2022-11-01","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":"2509.15155","title":"Self-Improving Embodied Foundation Models","created":"2025-09-18","cited_by_count":32,"area":"synth"},{"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":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30,"area":null},{"id":"2203.17138","title":"Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors","created":"2022-03-31","cited_by_count":30,"area":null},{"id":"2501.06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation","created":"2025-01-12","cited_by_count":30,"area":null},{"id":"2201.00206","title":"Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controller","created":"2022-01-01","cited_by_count":29,"area":null},{"id":"2203.05194","title":"Learning Torque Control for Quadrupedal Locomotion","created":"2022-03-10","cited_by_count":29,"area":null},{"id":"2205.05678","title":"RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation","created":"2022-05-11","cited_by_count":29,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2602.02454","title":"World-Gymnast: Training Robots with Reinforcement Learning in a World Model","created":"2026-02-02","cited_by_count":27,"area":"wm"},{"id":"2103.04909","title":"Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing","created":"2021-03-08","cited_by_count":26,"area":"wm"},{"id":"2312.03673","title":"On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer","created":"2023-12-06","cited_by_count":26,"area":null},{"id":"2101.05507","title":"Evaluating the Robustness of Collaborative Agents","created":"2021-01-14","cited_by_count":25,"area":null},{"id":"2104.09771","title":"GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model","created":"2021-04-20","cited_by_count":25,"area":null},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24,"area":null},{"id":"2510.20808","title":"The Reality Gap in Robotics: Challenges, Solutions, and Best Practices","created":"2025-10-23","cited_by_count":24,"area":null},{"id":"2109.14549","title":"Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization","created":"2021-09-29","cited_by_count":23,"area":null},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2103.06484","title":"Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":22,"area":null},{"id":"2105.10049","title":"Learning Modular Robot Control Policies","created":"2021-05-20","cited_by_count":22,"area":null},{"id":"2502.01536","title":"VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion","created":"2025-02-03","cited_by_count":22,"area":"deeprl"},{"id":"2510.15352","title":"GaussGym: An open-source real-to-sim framework for learning locomotion from pixels","created":"2025-10-17","cited_by_count":22,"area":null},{"id":"2105.09936","title":"BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image","created":"2021-05-20","cited_by_count":20,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2201.08434","title":"DROPO: Sim-to-Real Transfer with Offline Domain Randomization","created":"2022-01-20","cited_by_count":19,"area":null},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19,"area":null},{"id":"2505.22974","title":"Learning coordinated badminton skills for legged manipulators","created":"2025-05-29","cited_by_count":19,"area":"deeprl"},{"id":"2103.14331","title":"Imitation Learning from MPC for Quadrupedal Multi-Gait Control","created":"2021-03-26","cited_by_count":18,"area":"offlinerl"},{"id":"2108.03319","title":"Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning","created":"2021-08-06","cited_by_count":18,"area":null},{"id":"2202.07013","title":"Robust Policy Learning over Multiple Uncertainty Sets","created":"2022-02-14","cited_by_count":18,"area":null},{"id":"2209.14076","title":"Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems","created":"2022-09-28","cited_by_count":18,"area":null},{"id":"2303.03724","title":"Learning Bipedal Walking for Humanoids with Current Feedback","created":"2023-03-07","cited_by_count":18,"area":null},{"id":"2402.13820","title":"FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning","created":"2024-02-21","cited_by_count":18,"area":null},{"id":"2407.11562","title":"RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards","created":"2024-07-16","cited_by_count":18,"area":null},{"id":"2409.16784","title":"World Model-based Perception for Visual Legged Locomotion","created":"2024-09-25","cited_by_count":18,"area":"wm"},{"id":"2501.05204","title":"Design and Control of a Bipedal Robotic Character","created":"2025-01-09","cited_by_count":18,"area":null},{"id":"2109.08815","title":"Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation","created":"2021-09-18","cited_by_count":17,"area":null},{"id":"2209.12878","title":"Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization","created":"2022-09-26","cited_by_count":17,"area":null},{"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":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2407.18550","title":"ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments","created":"2024-07-26","cited_by_count":16,"area":null},{"id":"2409.04882","title":"Learning to Open and Traverse Doors with a Legged Manipulator","created":"2024-09-07","cited_by_count":16,"area":null},{"id":"2505.01458","title":"A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI","created":"2025-05-01","cited_by_count":16,"area":null},{"id":"2505.05753","title":"Towards Embodiment Scaling Laws in Robot Locomotion","created":"2025-05-09","cited_by_count":16,"area":null},{"id":"2407.02666","title":"Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models","created":"2024-07-02","cited_by_count":15,"area":"lr"},{"id":"2109.06409","title":"Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion","created":"2021-09-14","cited_by_count":14,"area":null},{"id":"2110.01388","title":"Neural Network Verification in Control","created":"2021-09-30","cited_by_count":14,"area":null},{"id":"2206.06282","title":"Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks","created":"2022-06-13","cited_by_count":14,"area":null},{"id":"2212.07740","title":"Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer","created":"2022-12-15","cited_by_count":14,"area":null},{"id":"2212.14400","title":"Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion","created":"2022-12-29","cited_by_count":14,"area":null},{"id":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2406.15149","title":"Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks","created":"2024-06-21","cited_by_count":14,"area":null},{"id":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"area":"alignment"}],"next_cursor":"100"}