{"total":382,"rows":[{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860,"area":"alignment"},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400,"area":"wm"},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295,"area":null},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211,"area":"vla"},{"id":"2406.10454","title":"HumanPlus: Humanoid Shadowing and Imitation from Humans","created":"2024-06-15","cited_by_count":185,"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":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164,"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":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"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":"2210.10044","title":"Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion","created":"2022-10-18","cited_by_count":121,"area":null},{"id":"2310.10943","title":"Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning","created":"2023-10-17","cited_by_count":111,"area":null},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106,"area":null},{"id":"2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","created":"2024-01-30","cited_by_count":99,"area":"deeprl"},{"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":"2309.06440","title":"LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning","created":"2023-09-12","cited_by_count":79,"area":null},{"id":"2401.17583","title":"Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion","created":"2024-01-31","cited_by_count":73,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62,"area":null},{"id":"2309.15462","title":"DTC: Deep Tracking Control","created":"2023-09-27","cited_by_count":56,"area":null},{"id":"2209.12827","title":"Advanced Skills by Learning Locomotion and Local Navigation End-to-End","created":"2022-09-26","cited_by_count":52,"area":null},{"id":"2509.10771","title":"RSL-RL: A Learning Library for Robotics Research","created":"2025-09-13","cited_by_count":49,"area":"deeprl"},{"id":"2405.01792","title":"Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots","created":"2024-05-03","cited_by_count":48,"area":null},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2502.10363","title":"BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds","created":"2025-02-14","cited_by_count":46,"area":null},{"id":"2206.11693","title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","created":"2022-06-23","cited_by_count":45,"area":null},{"id":"2210.04932","title":"NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields","created":"2022-10-10","cited_by_count":44,"area":null},{"id":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44,"area":null},{"id":"2305.08510","title":"Fast Traversability Estimation for Wild Visual Navigation","created":"2023-05-15","cited_by_count":44,"area":null},{"id":"2409.06366","title":"One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion","created":"2024-09-10","cited_by_count":43,"area":"deeprl"},{"id":"2403.02338","title":"Twisting Lids Off with Two Hands","created":"2024-03-04","cited_by_count":42,"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":"2303.11330","title":"Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion","created":"2023-03-20","cited_by_count":39,"area":null},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39,"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":"2203.14912","title":"Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning","created":"2022-03-23","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":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36,"area":null},{"id":"2504.17838","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards","created":"2025-04-24","cited_by_count":35,"area":"deeprl"},{"id":"2211.00458","title":"CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion","created":"2022-11-01","cited_by_count":34,"area":null},{"id":"2504.12609","title":"Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration","created":"2025-04-17","cited_by_count":34,"area":null},{"id":"2203.12071","title":"WayFAST: Navigation with Predictive Traversability in the Field","created":"2022-03-22","cited_by_count":32,"area":null},{"id":"2403.14864","title":"Learning Quadruped Locomotion Using Differentiable Simulation","created":"2024-03-21","cited_by_count":32,"area":null},{"id":"2408.06316","title":"Body Transformer: Leveraging Robot Embodiment for Policy Learning","created":"2024-08-12","cited_by_count":32,"area":null},{"id":"2406.12505","title":"Demonstrating Agile Flight from Pixels without State Estimation","created":"2024-06-18","cited_by_count":31,"area":"deeprl"},{"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":"2203.05194","title":"Learning Torque Control for Quadrupedal Locomotion","created":"2022-03-10","cited_by_count":29,"area":null},{"id":"2209.11221","title":"Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2305.12127","title":"DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training","created":"2023-05-20","cited_by_count":29,"area":null},{"id":"2405.07991","title":"SPIN: Simultaneous Perception, Interaction and Navigation","created":"2024-05-13","cited_by_count":29,"area":null},{"id":"2403.04359","title":"Symmetry Considerations for Learning Task Symmetric Robot Policies","created":"2024-03-07","cited_by_count":28,"area":null},{"id":"2402.10837","title":"Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg","created":"2024-02-16","cited_by_count":27,"area":null},{"id":"2305.04477","title":"Behavior Contrastive Learning for Unsupervised Skill Discovery","created":"2023-05-08","cited_by_count":26,"area":null},{"id":"2305.11252","title":"Brain-inspired learning in artificial neural networks: a review","created":"2023-05-18","cited_by_count":26,"area":null},{"id":"2305.17842","title":"RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion","created":"2023-05-29","cited_by_count":26,"area":null},{"id":"2211.03785","title":"Learning Visual Locomotion with Cross-Modal Supervision","created":"2022-11-07","cited_by_count":25,"area":null},{"id":"2405.10830","title":"CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion","created":"2024-05-17","cited_by_count":25,"area":"deeprl"},{"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":"2210.04435","title":"Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning","created":"2022-10-10","cited_by_count":23,"area":null},{"id":"2210.14791","title":"ViNL: Visual Navigation and Locomotion Over Obstacles","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2310.03581","title":"Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End","created":"2023-10-05","cited_by_count":23,"area":null},{"id":"2504.16693","title":"PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation","created":"2025-04-23","cited_by_count":22,"area":"wm"},{"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":"2203.15983","title":"VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2209.07899","title":"Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions","created":"2022-09-16","cited_by_count":21,"area":"offlinerl"},{"id":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","cited_by_count":21,"area":null},{"id":"2407.20230","title":"SAPG: Split and Aggregate Policy Gradients","created":"2024-07-29","cited_by_count":21,"area":"deeprl"},{"id":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2306.10014","title":"Coaching a Teachable Student","created":"2023-06-16","cited_by_count":19,"area":"distill"},{"id":"2310.01408","title":"Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior","created":"2023-10-02","cited_by_count":19,"area":null},{"id":"2310.10486","title":"ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots","created":"2023-10-16","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":"2602.15827","title":"Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching","created":"2026-02-17","cited_by_count":19,"area":null},{"id":"2210.05064","title":"VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement","created":"2022-10-11","cited_by_count":18,"area":null},{"id":"2310.15599","title":"Grasp Multiple Objects with One Hand","created":"2023-10-24","cited_by_count":18,"area":null},{"id":"2401.16337","title":"Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design","created":"2024-01-29","cited_by_count":18,"area":"deeprl"},{"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":"2209.12878","title":"Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization","created":"2022-09-26","cited_by_count":17,"area":null},{"id":"2404.07110","title":"Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervision","created":"2024-04-10","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":"2309.16683","title":"Controlling the Solo12 Quadruped Robot with Deep Reinforcement Learning","created":"2023-08-02","cited_by_count":16,"area":null},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","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":"2410.09163","title":"Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2505.00690","title":"Towards Autonomous Micromobility through Scalable Urban Simulation","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":"2307.10142","title":"Benchmarking Potential Based Rewards for Learning Humanoid Locomotion","created":"2023-07-19","cited_by_count":15,"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":"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":"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":"2405.12424","title":"Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers","created":"2024-05-21","cited_by_count":14,"area":"deeprl"},{"id":"2409.13678","title":"SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience","created":"2024-09-20","cited_by_count":14,"area":"deeprl"}],"next_cursor":"100"}