{"total":138,"rows":[{"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":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146,"area":"mllm"},{"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":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83,"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":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62,"area":null},{"id":"2312.14457","title":"QUAR-VLA: Vision-Language-Action Model for Quadruped Robots","created":"2023-12-22","cited_by_count":56,"area":"vla"},{"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":"2509.10771","title":"RSL-RL: A Learning Library for Robotics Research","created":"2025-09-13","cited_by_count":49,"area":"deeprl"},{"id":"2502.10363","title":"BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds","created":"2025-02-14","cited_by_count":46,"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":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39,"area":null},{"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":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36,"area":null},{"id":"2403.13358","title":"GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot","created":"2024-03-20","cited_by_count":29,"area":"moe"},{"id":"2503.08007","title":"MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models","created":"2025-03-11","cited_by_count":27,"area":"vla"},{"id":"2305.17842","title":"RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion","created":"2023-05-29","cited_by_count":26,"area":null},{"id":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","cited_by_count":26,"area":"offlinerl"},{"id":"2405.01402","title":"Learning Force Control for Legged Manipulation","created":"2024-05-02","cited_by_count":21,"area":null},{"id":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2302.04903","title":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","created":"2023-02-09","cited_by_count":18,"area":null},{"id":"2407.11562","title":"RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards","created":"2024-07-16","cited_by_count":18,"area":null},{"id":"2505.05753","title":"Towards Embodiment Scaling Laws in Robot Locomotion","created":"2025-05-09","cited_by_count":16,"area":null},{"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":"2407.10973","title":"Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2510.17792","title":"SoftMimic: Learning Compliant Whole-body Control from Examples","created":"2025-10-20","cited_by_count":14,"area":"deeprl"},{"id":"2403.09930","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics","created":"2024-03-15","cited_by_count":13,"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":"2411.07104","title":"Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing","created":"2024-11-11","cited_by_count":13,"area":null},{"id":"2602.18532","title":"VLANeXt: Recipes for Building Strong VLA Models","created":"2026-02-20","cited_by_count":12,"area":"mllm"},{"id":"2403.01410","title":"Barrier Functions Inspired Reward Shaping for Reinforcement Learning","created":"2024-03-03","cited_by_count":11,"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":"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":"2311.01405","title":"Learning to See Physical Properties with Active Sensing Motor Policies","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2506.08840","title":"MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains","created":"2025-06-10","cited_by_count":10,"area":"deeprl"},{"id":"2403.03848","title":"Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning","created":"2024-03-06","cited_by_count":9,"area":"deeprl"},{"id":"2310.05714","title":"DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies","created":"2023-10-09","cited_by_count":7,"area":"offlinerl"},{"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":"2306.04026","title":"Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2310.05022","title":"Fully Spiking Neural Network for Legged Robots","created":"2023-10-08","cited_by_count":6,"area":null},{"id":"2406.04835","title":"SLR: Learning Quadruped Locomotion without Privileged Information","created":"2024-06-07","cited_by_count":6,"area":"deeprl"},{"id":"2409.16048","title":"Whole-body End-Effector Pose Tracking","created":"2024-09-24","cited_by_count":6,"area":null},{"id":"2410.13837","title":"ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization","created":"2024-10-17","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":"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":"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":"2404.02176","title":"Versatile Navigation under Partial Observability via Value-guided Diffusion Policy","created":"2024-04-01","cited_by_count":5,"area":"diffusion"},{"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":"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":"2406.17279","title":"Learning Decentralized Multi-Biped Control for Payload Transport","created":"2024-06-25","cited_by_count":4,"area":null},{"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":"2509.02815","title":"Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization","created":"2025-09-02","cited_by_count":4,"area":null},{"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":"2512.00727","title":"Beyond Topology: A Morphological Symmetry Graph Representation for Locomotion Policy Learning","created":"2025-11-30","cited_by_count":4,"area":"deeprl"},{"id":"2608.20114","title":"DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation","created":"2026-08-20","cited_by_count":4,"area":"wm"},{"id":"2309.04370","title":"Seeing-Eye Quadruped Navigation with Force Responsive Locomotion Control","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2309.16718","title":"A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning","created":"2023-09-13","cited_by_count":3,"area":"offlinerl"},{"id":"2403.14300","title":"DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2405.19885","title":"Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning","created":"2024-05-30","cited_by_count":3,"area":"deeprl"},{"id":"2412.04323","title":"GRAM: Generalization in Deep RL with a Robust Adaptation Module","created":"2024-12-05","cited_by_count":3,"area":"deeprl"},{"id":"2503.01125","title":"TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning","created":"2025-03-03","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":"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":"2507.20382","title":"Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning","created":"2025-07-27","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":"2602.08370","title":"Learning Human-Like Badminton Skills for Humanoid Robots","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2312.16189","title":"OpenRL: A Unified Reinforcement Learning Framework","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2409.17992","title":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","created":"2024-09-26","cited_by_count":2,"area":"deeprl"},{"id":"2410.10438","title":"Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives","created":"2024-10-14","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":"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":"2504.14135","title":"Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering","created":"2025-04-19","cited_by_count":2,"area":null},{"id":"2505.02272","title":"Robust Localization, Mapping, and Navigation for Quadruped Robots","created":"2025-05-04","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":"2509.06296","title":"Learning to Walk With Less: A Dyna-Style Approach to Quadrupedal Locomotion","created":"2025-09-08","cited_by_count":2,"area":"deeprl"},{"id":"2510.20706","title":"Real-Time Gait Adaptation for Quadrupeds using Model Predictive Control and Reinforcement Learning","created":"2025-10-23","cited_by_count":2,"area":"deeprl"},{"id":"2602.00678","title":"Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion","created":"2026-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2607.18135","title":"Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds","created":"2026-07-20","cited_by_count":2,"area":"deeprl"},{"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":"2411.06782","title":"QuadWBG: Generalizable Quadrupedal Whole-Body Grasping","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2502.03717","title":"Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2502.12674","title":"SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2503.07049","title":"VMTS: Vision-Assisted Teacher-Student Reinforcement Learning for Multi-Terrain Locomotion in Bipedal Robots","created":"2025-03-10","cited_by_count":1,"area":"deeprl"},{"id":"2503.12406","title":"Bio-Inspired Plastic Neural Networks for Zero-Shot Out-of-Distribution Generalization in Complex Animal-Inspired Robots","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2505.00488","title":"MULE: Multi-terrain and Unknown Load Adaptation for Effective Quadrupedal Locomotion","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2508.03129","title":"Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection","created":"2025-08-05","cited_by_count":1,"area":"offlinerl"},{"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":"2509.12776","title":"Integrating Trajectory Optimization and Reinforcement Learning for Quadrupedal Jumping with Terrain-Adaptive Landing","created":"2025-09-16","cited_by_count":1,"area":"deeprl"},{"id":"2509.20635","title":"Learning Terrain-Specialized Policies for Adaptive Locomotion in Challenging Environments","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2605.08804","title":"Constraint-Aware Diffusion Priors for High-Fidelity and Versatile Quadruped Locomotion","created":"2026-05-09","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}