{"total":99,"rows":[{"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":"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":"2508.08241","title":"BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion","created":"2025-08-11","cited_by_count":165,"area":"diffusion"},{"id":"2402.16796","title":"Expressive Whole-Body Control for Humanoid Robots","created":"2024-02-26","cited_by_count":139,"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":"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":"2412.13196","title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","created":"2024-12-17","cited_by_count":88,"area":null},{"id":"2502.13013","title":"HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit","created":"2025-02-18","cited_by_count":76,"area":null},{"id":"2509.26633","title":"OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction","created":"2025-09-30","cited_by_count":71,"area":"deeprl"},{"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":"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":"2502.08378","title":"Learning Humanoid Standing-up Control across Diverse Postures","created":"2025-02-12","cited_by_count":46,"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":"2505.07294","title":"HuB: Learning Extreme Humanoid Balance","created":"2025-05-12","cited_by_count":28,"area":null},{"id":"2403.17320","title":"Leveraging Symmetry in RL-based Legged Locomotion Control","created":"2024-03-26","cited_by_count":25,"area":"deeprl"},{"id":"2409.18382","title":"CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models","created":"2024-09-27","cited_by_count":22,"area":null},{"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":"2502.09614","title":"DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References","created":"2025-02-13","cited_by_count":17,"area":"deeprl"},{"id":"2510.14959","title":"CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions","created":"2025-10-16","cited_by_count":17,"area":"deeprl"},{"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":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"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":"2602.02473","title":"HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos","created":"2026-02-02","cited_by_count":14,"area":null},{"id":"2502.10894","title":"Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation","created":"2025-02-15","cited_by_count":13,"area":null},{"id":"2502.16230","title":"Learning Humanoid Locomotion with World Model Reconstruction","created":"2025-02-22","cited_by_count":13,"area":"wm"},{"id":"2509.16638","title":"KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control","created":"2025-09-20","cited_by_count":13,"area":null},{"id":"2405.15384","title":"Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate","created":"2024-05-24","cited_by_count":10,"area":"deeprl"},{"id":"2410.08655","title":"FRASA: An End-to-End Reinforcement Learning Agent for Fall Recovery and Stand Up of Humanoid Robots","created":"2024-10-11","cited_by_count":10,"area":"deeprl"},{"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":"2504.04191","title":"GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill","created":"2025-04-05","cited_by_count":9,"area":null},{"id":"2503.15082","title":"StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion","created":"2025-03-19","cited_by_count":8,"area":"deeprl"},{"id":"2510.14454","title":"Towards Adaptable Humanoid Control via Adaptive Motion Tracking","created":"2025-10-16","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":"2406.14655","title":"HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2409.16611","title":"Achieving Stable High-Speed Locomotion for Humanoid Robots with Deep Reinforcement Learning","created":"2024-09-25","cited_by_count":6,"area":"deeprl"},{"id":"2410.07877","title":"Constrained Skill Discovery: Quadruped Locomotion with Unsupervised Reinforcement Learning","created":"2024-10-10","cited_by_count":6,"area":"deeprl"},{"id":"2510.11682","title":"Ego-Vision World Model for Humanoid Contact Planning","created":"2025-10-13","cited_by_count":6,"area":"wm"},{"id":"2512.05094","title":"From Generated Human Videos to Physically Plausible Robot Trajectories","created":"2025-12-04","cited_by_count":6,"area":null},{"id":"2602.15733","title":"MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction","created":"2026-02-17","cited_by_count":6,"area":"deeprl"},{"id":"2405.07444","title":"Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction","created":"2024-05-13","cited_by_count":5,"area":null},{"id":"2503.20839","title":"TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion","created":"2025-03-26","cited_by_count":5,"area":"distill"},{"id":"2508.09354","title":"CLF-RL: Control Lyapunov Function Guided Reinforcement Learning","created":"2025-08-12","cited_by_count":5,"area":"deeprl"},{"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":"2407.06584","title":"HiLMa-Res: A General Hierarchical Framework via Residual RL for Combining Quadrupedal Locomotion and Manipulation","created":"2024-07-09","cited_by_count":4,"area":"deeprl"},{"id":"2509.11149","title":"RoVerFly: Robust and Versatile Implicit Hybrid Control of Quadrotor-Payload Systems","created":"2025-09-14","cited_by_count":4,"area":null},{"id":"2509.19573","title":"Chasing Stability: Humanoid Running via Control Lyapunov Function Guided Reinforcement Learning","created":"2025-09-23","cited_by_count":4,"area":"deeprl"},{"id":"2509.23846","title":"Adversarial Diffusion for Robust Reinforcement Learning","created":"2025-09-28","cited_by_count":4,"area":"diffusion"},{"id":"2512.25072","title":"Coordinated Humanoid Manipulation with Choice Policies","created":"2025-12-31","cited_by_count":4,"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":"2505.20857","title":"Multi-Embodiment Robotic Retargeting via Guided Diffusion Model","created":"2025-05-27","cited_by_count":3,"area":"diffusion"},{"id":"2506.00472","title":"Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots","created":"2025-05-31","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":"2509.16061","title":"Latent Conditioned Loco-Manipulation Using Motion Priors","created":"2025-09-19","cited_by_count":3,"area":"deeprl"},{"id":"2511.11218","title":"Humanoid Whole-Body Badminton via an Annealed Reinforcement Learning Curriculum","created":"2025-11-14","cited_by_count":3,"area":"deeprl"},{"id":"2606.08610","title":"HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning","created":"2026-06-07","cited_by_count":3,"area":"agents"},{"id":"2411.13079","title":"Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2504.00614","title":"Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs","created":"2025-04-01","cited_by_count":2,"area":"deeprl"},{"id":"2506.02507","title":"AURA: Autonomous Upskilling with Retrieval-Augmented Agents","created":"2025-06-03","cited_by_count":2,"area":"rag"},{"id":"2508.01247","title":"Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy","created":"2025-08-02","cited_by_count":2,"area":"deeprl"},{"id":"2601.16109","title":"Efficiently Learning Robust Torque-based Locomotion Through Reinforcement with Model-Based Supervision","created":"2026-01-22","cited_by_count":2,"area":"deeprl"},{"id":"2603.08619","title":"Embedding Classical Balance Control Principles in Reinforcement Learning for Humanoid Recovery","created":"2026-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2603.27944","title":"Flip Stunts on Bicycle Robots using Iterative Motion Imitation","created":"2026-03-30","cited_by_count":2,"area":"deeprl"},{"id":"2604.08958","title":"WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning","created":"2026-04-10","cited_by_count":2,"area":"wm"},{"id":"2604.10974","title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","created":"2026-04-13","cited_by_count":2,"area":"deeprl"},{"id":"2606.16447","title":"Training and Evaluating Diffusion Policies with Long Context Lengths","created":"2026-06-15","cited_by_count":2,"area":"diffusion"},{"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":"2411.15350","title":"Dynamic Tube MPC: Learning Tube Dynamics with Massively Parallel Simulation for Robust Safety in Practice","created":"2024-11-22","cited_by_count":1,"area":null},{"id":"2506.01665","title":"Leveraging Analytic Gradients in Provably Safe Reinforcement Learning","created":"2025-06-02","cited_by_count":1,"area":"deeprl"},{"id":"2508.02194","title":"Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot","created":"2025-08-04","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":"2509.05581","title":"Learning to Walk in Costume: Adversarial Motion Priors for Aesthetically Constrained Humanoids","created":"2025-09-06","cited_by_count":1,"area":"deeprl"},{"id":"2509.20696","title":"RuN: Residual Policy for Natural Humanoid Locomotion","created":"2025-09-25","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":"2602.06967","title":"Leveraging Adaptive Group Negotiation for Heterogeneous Multi-Robot Collaboration with Large Language Models","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2605.05110","title":"LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2501.11945","title":"Learning to Hop for a Single-Legged Robot with Parallel Mechanism","created":"2025-01-21","cited_by_count":0,"area":"deeprl"},{"id":"2503.08259","title":"Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policy","created":"2025-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2504.14103","title":"Coordinating Spinal and Limb Dynamics for Enhanced Sprawling Robot Mobility","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2505.04193","title":"Trajectory Entropy Reinforcement Learning for Robust Robot Motor Skill Learning","created":"2025-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2505.06561","title":"Quadrupedal Robot Skateboard Mounting via Reverse Curriculum Learning","created":"2025-05-10","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":"2602.05596","title":"TOLEBI: Learning Fault-Tolerant Bipedal Locomotion via Online Status Estimation and Fallibility Rewards","created":"2026-02-05","cited_by_count":0,"area":"deeprl"},{"id":"2602.21119","title":"Cooperative-Competitive Team Play of Real-World Craft Robots","created":"2026-02-24","cited_by_count":0,"area":"deeprl"},{"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":"2604.12909","title":"Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots","created":"2026-04-14","cited_by_count":0,"area":"deeprl"},{"id":"2604.19104","title":"Reinforcement Learning Enabled Adaptive Multi-Task Control for Bipedal Soccer Robots","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2604.23702","title":"QuietWalk: Physics-Informed Reinforcement Learning for Ground Reaction Force-Aware Humanoid Locomotion Under Diverse Footwear","created":"2026-04-26","cited_by_count":0,"area":"deeprl"},{"id":"2605.28549","title":"SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.02636","title":"Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.22145","title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","created":"2026-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.01410","title":"BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.24083","title":"Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.06907","title":"Spatiotemporal Agility: Time-Constrained Reinforcement Learning for Vision-Guided Dynamic Quadrupedal Interception","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.02358","title":"Humanoid Safe Stop via Learned Stoppability Value","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.15988","title":"ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids","created":"2026-09-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}