{"total":92,"rows":[{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512,"area":"wm"},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400,"area":"wm"},{"id":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187,"area":null},{"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":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149,"area":null},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145,"area":"offlinerl"},{"id":"2402.16796","title":"Expressive Whole-Body Control for Humanoid Robots","created":"2024-02-26","cited_by_count":139,"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":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130,"area":"deeprl"},{"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":"2202.05481","title":"Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion","created":"2022-02-11","cited_by_count":88,"area":null},{"id":"2412.13196","title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","created":"2024-12-17","cited_by_count":88,"area":null},{"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":"2205.15299","title":"Adapting Rapid Motor Adaptation for Bipedal Robots","created":"2022-05-30","cited_by_count":54,"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":"2412.07773","title":"Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control","created":"2024-12-10","cited_by_count":51,"area":null},{"id":"2505.03738","title":"AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control","created":"2025-05-06","cited_by_count":51,"area":null},{"id":"2110.15344","title":"Learning to Jump from Pixels","created":"2021-10-28","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":"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":"2304.01159","title":"DribbleBot: Dynamic Legged Manipulation in the Wild","created":"2023-04-03","cited_by_count":40,"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":"2402.18294","title":"Whole-body Humanoid Robot Locomotion with Human Reference","created":"2024-02-28","cited_by_count":29,"area":"offlinerl"},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26,"area":"offlinerl"},{"id":"2410.03654","title":"Learning Humanoid Locomotion over Challenging Terrain","created":"2024-10-04","cited_by_count":26,"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":"2503.12533","title":"Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills","created":"2025-03-16","cited_by_count":22,"area":"agents"},{"id":"2107.06629","title":"Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimization","created":"2021-07-14","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":"2303.03724","title":"Learning Bipedal Walking for Humanoids with Current Feedback","created":"2023-03-07","cited_by_count":18,"area":null},{"id":"2501.05204","title":"Design and Control of a Bipedal Robotic Character","created":"2025-01-09","cited_by_count":18,"area":null},{"id":"2201.09562","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","created":"2022-01-24","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":"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":"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"},{"id":"2409.15755","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","created":"2024-09-24","cited_by_count":13,"area":"deeprl"},{"id":"2502.16230","title":"Learning Humanoid Locomotion with World Model Reconstruction","created":"2025-02-22","cited_by_count":13,"area":"wm"},{"id":"2601.07718","title":"Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids","created":"2026-01-12","cited_by_count":13,"area":null},{"id":"2206.08077","title":"Neural Scene Representation for Locomotion on Structured Terrain","created":"2022-06-16","cited_by_count":12,"area":null},{"id":"2207.12644","title":"Learning Bipedal Walking On Planned Footsteps For Humanoid Robots","created":"2022-07-26","cited_by_count":12,"area":null},{"id":"2209.14887","title":"Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion","created":"2022-09-29","cited_by_count":12,"area":null},{"id":"2503.08299","title":"Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion","created":"2025-03-11","cited_by_count":10,"area":"deeprl"},{"id":"2303.09597","title":"Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2304.10888","title":"Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2402.06143","title":"Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots","created":"2024-02-09","cited_by_count":8,"area":"deeprl"},{"id":"2404.17070","title":"Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey","created":"2024-04-25","cited_by_count":7,"area":"deeprl"},{"id":"2402.06783","title":"Learn to Teach: Sample-Efficient Privileged Learning for Humanoid Locomotion over Diverse Terrains","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2505.20619","title":"Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion","created":"2025-05-27","cited_by_count":6,"area":"deeprl"},{"id":"2302.13378","title":"Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive","created":"2023-02-26","cited_by_count":5,"area":null},{"id":"2309.16074","title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning","created":"2023-09-28","cited_by_count":5,"area":"offlinerl"},{"id":"2508.03070","title":"Optimizing Bipedal Locomotion for The 100m Dash With Comparison to Human Running","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2512.07464","title":"Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction","created":"2025-12-08","cited_by_count":5,"area":"deeprl"},{"id":"2111.00262","title":"Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner","created":"2021-10-30","cited_by_count":4,"area":null},{"id":"2203.02857","title":"Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulations","created":"2022-03-06","cited_by_count":4,"area":null},{"id":"2402.00366","title":"Legged Robot State Estimation With Invariant Extended Kalman Filter Using Neural Measurement Network","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2406.17279","title":"Learning Decentralized Multi-Biped Control for Payload Transport","created":"2024-06-25","cited_by_count":4,"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":"2409.08904","title":"AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2411.01000","title":"Enhancing Model-Based Step Adaptation for Push Recovery through Reinforcement Learning of Step Timing and Region","created":"2024-11-01","cited_by_count":3,"area":"deeprl"},{"id":"2504.13619","title":"Robust Humanoid Walking on Compliant and Uneven Terrain with Deep Reinforcement Learning","created":"2025-04-18","cited_by_count":3,"area":"deeprl"},{"id":"2508.11929","title":"No More Blind Spots: Learning Vision-Based Omnidirectional Bipedal Locomotion for Challenging Terrain","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2509.12858","title":"Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion","created":"2025-09-16","cited_by_count":3,"area":"deeprl"},{"id":"2111.02371","title":"What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2503.08349","title":"LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures","created":"2025-03-11","cited_by_count":2,"area":"deeprl"},{"id":"2503.17626","title":"Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots","created":"2025-03-22","cited_by_count":2,"area":"deeprl"},{"id":"2509.09106","title":"LIPM-Guided Reinforcement Learning for Stable and Perceptive Locomotion in Bipedal Robots","created":"2025-09-11","cited_by_count":2,"area":"deeprl"},{"id":"2403.04205","title":"OGMP: Oracle Guided Multi-mode Policies for Agile and Versatile Robot Control","created":"2024-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2409.16301","title":"Gait Switching and Enhanced Stabilization of Walking Robots with Deep Learning-based Reachability: A Case Study on Two-link Walker","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2509.20696","title":"RuN: Residual Policy for Natural Humanoid Locomotion","created":"2025-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2510.14947","title":"Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotion","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2604.10165","title":"MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks","created":"2026-04-11","cited_by_count":1,"area":"offlinerl"},{"id":"2109.05604","title":"Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies","created":"2021-09-12","cited_by_count":0,"area":null},{"id":"2204.04157","title":"Custom Sine Waves Are Enough for Imitation Learning of Bipedal Gaits with Different Styles","created":"2022-04-08","cited_by_count":0,"area":"offlinerl"},{"id":"2303.02386","title":"Modular Safety-Critical Control of Legged Robots","created":"2023-03-04","cited_by_count":0,"area":null},{"id":"2405.17227","title":"Learning Generic and Dynamic Locomotion of Humanoids Across Discrete Terrains","created":"2024-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2505.19054","title":"RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2506.17823","title":"Learning to Dock: A Simulation-based Study on Closing the Sim2Real Gap in Autonomous Underwater Docking","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2507.15649","title":"EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation","created":"2025-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2508.14098","title":"No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2509.18046","title":"HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba","created":"2025-09-22","cited_by_count":0,"area":"ssm"},{"id":"2512.12993","title":"Learning Terrain Aware Bipedal Locomotion via Reduced Dimensional Perceptual Representations","created":"2025-12-15","cited_by_count":0,"area":"deeprl"},{"id":"2603.26687","title":"Learning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.08036","title":"PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPC","created":"2026-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2605.19503","title":"ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.04718","title":"CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation","created":"2026-06-03","cited_by_count":0,"area":"moe"},{"id":"2610.04238","title":"Humanoid Rickshaw Pulling: Whole-Body Locomotion under Coupled Wheeled Loads","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}