{"total":149,"rows":[{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218,"area":null},{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164,"area":null},{"id":"2502.05450","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","created":"2025-02-08","cited_by_count":154,"area":"vla"},{"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":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112,"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":"2409.10161","title":"SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting","created":"2024-09-16","cited_by_count":69,"area":null},{"id":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62,"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":"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":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49,"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":"2309.09969","title":"Prompt a Robot to Walk with Large Language Models","created":"2023-09-18","cited_by_count":45,"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":"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":"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":"2403.12203","title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","created":"2024-03-18","cited_by_count":31,"area":"deeprl"},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"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":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2503.08564","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion","created":"2025-03-11","cited_by_count":23,"area":"moe"},{"id":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22,"area":null},{"id":"2502.01536","title":"VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion","created":"2025-02-03","cited_by_count":22,"area":"deeprl"},{"id":"2405.01402","title":"Learning Force Control for Legged Manipulation","created":"2024-05-02","cited_by_count":21,"area":null},{"id":"2403.20328","title":"Learning Visual Quadrupedal Loco-Manipulation from Demonstrations","created":"2024-03-29","cited_by_count":20,"area":null},{"id":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2310.01408","title":"Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior","created":"2023-10-02","cited_by_count":19,"area":null},{"id":"2409.05864","title":"Neural MP: A Generalist Neural Motion Planner","created":"2024-09-09","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":"2409.16784","title":"World Model-based Perception for Visual Legged Locomotion","created":"2024-09-25","cited_by_count":18,"area":"wm"},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","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":"2405.00846","title":"Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination","created":"2024-05-01","cited_by_count":16,"area":null},{"id":"2411.01775","title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","created":"2024-11-04","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":"2404.09080","title":"Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications","created":"2024-04-13","cited_by_count":15,"area":"deeprl"},{"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":"2509.14353","title":"DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion","created":"2025-09-17","cited_by_count":15,"area":"diffusion"},{"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":"2502.12465","title":"Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification","created":"2025-02-18","cited_by_count":13,"area":"offlinerl"},{"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":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2502.17219","title":"Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning","created":"2025-02-24","cited_by_count":11,"area":"deeprl"},{"id":"2503.03045","title":"ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation","created":"2025-03-04","cited_by_count":11,"area":null},{"id":"2505.06883","title":"FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots","created":"2025-05-11","cited_by_count":11,"area":"deeprl"},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2509.02530","title":"Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots","created":"2025-09-02","cited_by_count":11,"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":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9,"area":"deeprl"},{"id":"2407.15134","title":"Proximal Policy Distillation","created":"2024-07-21","cited_by_count":9,"area":"distill"},{"id":"2412.09989","title":"One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments","created":"2024-12-13","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":"2407.04224","title":"PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots","created":"2024-07-05","cited_by_count":8,"area":"deeprl"},{"id":"2410.00231","title":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2503.08375","title":"Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion","created":"2025-03-11","cited_by_count":8,"area":"deeprl"},{"id":"2407.16186","title":"Automatic Environment Shaping is the Next Frontier in RL","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2409.07409","title":"Robust Robot Walker: Learning Agile Locomotion over Tiny Traps","created":"2024-09-11","cited_by_count":7,"area":null},{"id":"2409.09441","title":"PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion","created":"2024-09-14","cited_by_count":7,"area":null},{"id":"2410.13586","title":"Preference Aligned Diffusion Planner for Quadrupedal Locomotion Control","created":"2024-10-17","cited_by_count":7,"area":"diffusion"},{"id":"2502.01465","title":"Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions","created":"2025-02-03","cited_by_count":7,"area":"deeprl"},{"id":"2406.04835","title":"SLR: Learning Quadruped Locomotion without Privileged Information","created":"2024-06-07","cited_by_count":6,"area":"deeprl"},{"id":"2408.09662","title":"CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control","created":"2024-08-19","cited_by_count":6,"area":"deeprl"},{"id":"2409.19709","title":"DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"id":"2410.10766","title":"Adaptive Diffusion Terrain Generator for Autonomous Uneven Terrain Navigation","created":"2024-10-14","cited_by_count":6,"area":"diffusion"},{"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":"2508.08982","title":"Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion","created":"2025-08-12","cited_by_count":6,"area":null},{"id":"2601.07701","title":"Deep Whole-body Parkour","created":"2026-01-12","cited_by_count":6,"area":null},{"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":"2505.18780","title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","created":"2025-05-24","cited_by_count":5,"area":"wm"},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"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":"2411.01850","title":"ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2501.05057","title":"LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models","created":"2025-01-09","cited_by_count":4,"area":"driving"},{"id":"2501.09905","title":"SLIM: Sim-to-Real Legged Instructive Manipulation via Long-Horizon Visuomotor Learning","created":"2025-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2503.19037","title":"Evolutionary Policy Optimization","created":"2025-03-24","cited_by_count":4,"area":"deeprl"},{"id":"2509.20036","title":"MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping","created":"2025-09-24","cited_by_count":4,"area":"deeprl"},{"id":"2401.15484","title":"R$\\times$R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training","created":"2024-01-27","cited_by_count":3,"area":"deeprl"},{"id":"2408.12674","title":"One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs","created":"2024-08-22","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":"2505.13834","title":"Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams","created":"2025-05-20","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":"2510.03207","title":"To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning","created":"2025-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2511.14427","title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","created":"2025-11-18","cited_by_count":3,"area":"deeprl"},{"id":"2512.09571","title":"Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racing","created":"2025-12-10","cited_by_count":3,"area":"deeprl"},{"id":"2602.08370","title":"Learning Human-Like Badminton Skills for Humanoid Robots","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2404.15256","title":"TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2409.11403","title":"UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning","created":"2024-09-17","cited_by_count":2,"area":"deeprl"},{"id":"2412.04273","title":"Reinforcement Learning from Wild Animal Videos","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2502.15442","title":"Learning Long-Horizon Robot Manipulation Skills via Privileged Action","created":"2025-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2503.05035","title":"QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2508.07611","title":"End-to-End Humanoid Robot Safe and Comfortable Locomotion Policy","created":"2025-08-11","cited_by_count":2,"area":"deeprl"},{"id":"2601.02778","title":"Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2602.21203","title":"Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics","created":"2026-02-24","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":"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":"2404.08246","title":"Agile and versatile bipedal robot tracking control through reinforcement learning","created":"2024-04-12","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}