{"total":37,"rows":[{"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":"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":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"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":"2103.14295","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","created":"2021-03-26","cited_by_count":116,"area":null},{"id":"2104.04644","title":"Fast and Efficient Locomotion via Learned Gait Transitions","created":"2021-04-09","cited_by_count":54,"area":null},{"id":"2205.15299","title":"Adapting Rapid Motor Adaptation for Bipedal Robots","created":"2022-05-30","cited_by_count":54,"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":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"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":"2506.12779","title":"From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots","created":"2025-06-15","cited_by_count":17,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"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":"2207.13224","title":"PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations","created":"2022-07-27","cited_by_count":10,"area":null},{"id":"2212.08954","title":"Cascaded Compositional Residual Learning for Complex Interactive Behaviors","created":"2022-12-17","cited_by_count":10,"area":null},{"id":"2310.14526","title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2101.05317","title":"Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning","created":"2021-01-13","cited_by_count":7,"area":null},{"id":"2307.16890","title":"Discovering Adaptable Symbolic Algorithms from Scratch","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2304.12289","title":"Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics","created":"2023-04-24","cited_by_count":3,"area":null},{"id":"2310.10606","title":"BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2312.15474","title":"A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning","created":"2023-12-24","cited_by_count":3,"area":null},{"id":"2407.11069","title":"Combining Federated Learning and Control: A Survey","created":"2024-07-12","cited_by_count":3,"area":null},{"id":"2502.11377","title":"PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2504.16923","title":"Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2111.14352","title":"Physics-informed Evolutionary Strategy based Control for Mitigating Delayed Voltage Recovery","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2309.04085","title":"ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agents","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2510.01708","title":"PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2109.12696","title":"PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotion","created":"2021-09-26","cited_by_count":1,"area":null},{"id":"2202.05843","title":"Fast Model-based Policy Search for Universal Policy Networks","created":"2022-02-11","cited_by_count":1,"area":null},{"id":"2404.15096","title":"Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robot","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2602.16705","title":"HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2103.07732","title":"Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments","created":"2021-03-13","cited_by_count":0,"area":null},{"id":"2308.14652","title":"Learning Visual Tracking and Reaching with Deep Reinforcement Learning on a UR10e Robotic Arm","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2505.12361","title":"Adaptive MPC-based quadrupedal robot control under periodic disturbances","created":"2025-05-18","cited_by_count":0,"area":null}],"next_cursor":null}