{"total":96,"rows":[{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312,"area":"lr"},{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189,"area":null},{"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":"2212.03238","title":"Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior","created":"2022-12-06","cited_by_count":138,"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":"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":"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":"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":"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":"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":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36,"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":"2402.18294","title":"Whole-body Humanoid Robot Locomotion with Human Reference","created":"2024-02-28","cited_by_count":29,"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":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","cited_by_count":24,"area":null},{"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":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"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":"2408.07295","title":"Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robots","created":"2024-07-30","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":"2207.12644","title":"Learning Bipedal Walking On Planned Footsteps For Humanoid Robots","created":"2022-07-26","cited_by_count":12,"area":null},{"id":"2409.15780","title":"A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards","created":"2024-09-24","cited_by_count":12,"area":"deeprl"},{"id":"2502.03206","title":"A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2204.04340","title":"Sim-to-Real Learning for Bipedal Locomotion Under Unsensed Dynamic Loads","created":"2022-04-09","cited_by_count":10,"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":"2510.08556","title":"DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model","created":"2025-10-09","cited_by_count":9,"area":null},{"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":"2404.17070","title":"Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey","created":"2024-04-25","cited_by_count":7,"area":"deeprl"},{"id":"2107.10969","title":"Learning Quadruped Locomotion Policies using Logical Rules","created":"2021-07-23","cited_by_count":6,"area":null},{"id":"2304.06193","title":"Learning Over Contracting and Lipschitz Closed-Loops for Partially-Observed Nonlinear Systems (Extended Version)","created":"2023-04-12","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":"2203.02570","title":"Bayesian Optimization Meets Hybrid Zero Dynamics: Safe Parameter Learning for Bipedal Locomotion Control","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2205.05787","title":"Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models","created":"2022-05-11","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":"2403.20001","title":"Adaptive Energy Regularization for Autonomous Gait Transition and Energy-Efficient Quadruped Locomotion","created":"2024-03-29","cited_by_count":5,"area":"deeprl"},{"id":"2506.07876","title":"Versatile Loco-Manipulation through Flexible Interlimb Coordination","created":"2025-06-09","cited_by_count":5,"area":"deeprl"},{"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":"2509.01765","title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control","created":"2025-09-01","cited_by_count":5,"area":"deeprl"},{"id":"2112.04741","title":"Learning multiple gaits of quadruped robot using hierarchical reinforcement learning","created":"2021-12-09","cited_by_count":4,"area":null},{"id":"2306.17411","title":"Decentralized Motor Skill Learning for Complex Robotic Systems","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2406.16578","title":"QuadrupedGPT: Towards a Versatile Quadruped Agent in Open-ended Worlds","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2603.16188","title":"ECHO: Edge-Cloud Humanoid Orchestration for Language-to-Motion Control","created":"2026-03-17","cited_by_count":4,"area":"diffusion"},{"id":"2304.13150","title":"Roll-Drop: accounting for observation noise with a single parameter","created":"2023-04-25","cited_by_count":3,"area":null},{"id":"2408.15632","title":"Structural Optimization of Lightweight Bipedal Robot via SERL","created":"2024-08-28","cited_by_count":3,"area":"deeprl"},{"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":"2504.08246","title":"Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid Locomotion","created":"2025-04-11","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":"2506.15132","title":"Booster Gym: An End-to-End Reinforcement Learning Framework for Humanoid Robot Locomotion","created":"2025-06-18","cited_by_count":3,"area":"deeprl"},{"id":"2507.05674","title":"Integrating Diffusion-based Multi-task Learning with Online Reinforcement Learning for Robust Quadruped Robot Control","created":"2025-07-08","cited_by_count":3,"area":"diffusion"},{"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":"2509.20717","title":"RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking","created":"2025-09-25","cited_by_count":3,"area":"deeprl"},{"id":"2210.04819","title":"Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors","created":"2022-10-10","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":"2510.11542","title":"NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning","created":"2025-10-13","cited_by_count":2,"area":"deeprl"},{"id":"2512.13093","title":"PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2305.11107","title":"From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2306.08224","title":"Expanding Versatility of Agile Locomotion through Policy Transitions Using Latent State Representation","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2306.12612","title":"RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2402.08662","title":"Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedback","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2409.07846","title":"Learning Skateboarding for Humanoid Robots through Massively Parallel Reinforcement Learning","created":"2024-09-12","cited_by_count":1,"area":"deeprl"},{"id":"2508.04696","title":"Achieving Precise and Reliable Locomotion with Differentiable Simulation-Based System Identification","created":"2025-08-06","cited_by_count":1,"area":"deeprl"},{"id":"2508.10423","title":"MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2511.06465","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Bipedal Locomotion","created":"2025-11-09","cited_by_count":1,"area":"deeprl"},{"id":"2602.06445","title":"ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking","created":"2026-02-06","cited_by_count":1,"area":"deeprl"},{"id":"2606.08253","title":"Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.26392","title":"MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins","created":"2026-06-24","cited_by_count":1,"area":"deeprl"},{"id":"2203.01968","title":"Learning Time-optimized Path Tracking with or without Sensory Feedback","created":"2022-03-03","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":"2306.15793","title":"A Population-Level Analysis of Neural Dynamics in Robust Legged Robots","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2312.10328","title":"Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking","created":"2023-12-16","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":"2506.08416","title":"A Gait Driven Reinforcement Learning Framework for Humanoid Robots","created":"2025-06-10","cited_by_count":0,"area":"deeprl"},{"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":"2603.17468","title":"Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.21853","title":"Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.16440","title":"LatentMimic: Terrain-Adaptive Locomotion via Latent Space Imitation","created":"2026-04-07","cited_by_count":0,"area":null},{"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":"2606.13169","title":"Redesigning Regularization for Effective Policy Smoothing","created":"2026-06-11","cited_by_count":0,"area":"deeprl"},{"id":"2607.12114","title":"GaitSpan: Growing Humanoid Locomotion from Walking to Running","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.17320","title":"Robust Brachiation on a Life-Sized Dual-Arm Robot Using Waypoint-Guided Reinforcement Learning","created":"2026-08-18","cited_by_count":0,"area":"deeprl"},{"id":"2609.06958","title":"Mind the Phase: Effective Rank and Representation Health in Legged Locomotion","created":"2026-09-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.17824","title":"Learning Multi-Humanoid Pickup and Transport via Decentralized Object-Centric Control","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.05855","title":"Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated Biped","created":"2026-10-05","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}