{"total":152,"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":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164,"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":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68,"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":"2509.10771","title":"RSL-RL: A Learning Library for Robotics Research","created":"2025-09-13","cited_by_count":49,"area":"deeprl"},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2308.15143","title":"Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models","created":"2023-08-29","cited_by_count":37,"area":null},{"id":"2505.04002","title":"PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers","created":"2025-05-06","cited_by_count":28,"area":"deeprl"},{"id":"2402.10837","title":"Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg","created":"2024-02-16","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":"2310.03581","title":"Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End","created":"2023-10-05","cited_by_count":23,"area":null},{"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":"2510.15352","title":"GaussGym: An open-source real-to-sim framework for learning locomotion from pixels","created":"2025-10-17","cited_by_count":22,"area":null},{"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":"2310.01408","title":"Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior","created":"2023-10-02","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":"2401.16337","title":"Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design","created":"2024-01-29","cited_by_count":18,"area":"deeprl"},{"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":"2405.02425","title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":17,"area":"deeprl"},{"id":"2411.01775","title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","created":"2024-11-04","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":"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":"2502.16230","title":"Learning Humanoid Locomotion with World Model Reconstruction","created":"2025-02-22","cited_by_count":13,"area":"wm"},{"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":"2602.00401","title":"ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2412.03012","title":"Learning Whole-Body Loco-Manipulation for Omni-Directional Task Space Pose Tracking with a Wheeled-Quadrupedal-Manipulator","created":"2024-12-04","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":"2504.17857","title":"High-Performance Reinforcement Learning on Spot: Optimizing Simulation Parameters with Distributional Measures","created":"2025-04-24","cited_by_count":10,"area":"deeprl"},{"id":"2310.02440","title":"Learning Diverse Skills for Local Navigation under Multi-constraint Optimality","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2405.19452","title":"Gaitor: Learning a Unified Representation Across Gaits for Real-World Quadruped Locomotion","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2512.16705","title":"Olaf: Bringing an Animated Character to Life in the Physical World","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2406.14655","title":"HYPERmotion: Learning Hybrid Behavior Planning for Autonomous Loco-manipulation","created":"2024-06-20","cited_by_count":7,"area":null},{"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":"2502.01465","title":"Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions","created":"2025-02-03","cited_by_count":7,"area":"deeprl"},{"id":"2506.11470","title":"Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion","created":"2025-06-13","cited_by_count":7,"area":"diffusion"},{"id":"2602.12691","title":"ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training","created":"2026-02-13","cited_by_count":7,"area":"vla"},{"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":"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":"2410.07877","title":"Constrained Skill Discovery: Quadruped Locomotion with Unsupervised Reinforcement Learning","created":"2024-10-10","cited_by_count":6,"area":"deeprl"},{"id":"2602.18424","title":"CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation","created":"2026-02-20","cited_by_count":6,"area":"mllm"},{"id":"2505.16084","title":"Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility","created":"2025-05-21","cited_by_count":5,"area":"deeprl"},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2604.04539","title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","created":"2026-04-06","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":"2507.16481","title":"Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots","created":"2025-07-22","cited_by_count":4,"area":"deeprl"},{"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":"2509.20036","title":"MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping","created":"2025-09-24","cited_by_count":4,"area":"deeprl"},{"id":"2408.15632","title":"Structural Optimization of Lightweight Bipedal Robot via SERL","created":"2024-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2409.19617","title":"LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World","created":"2024-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2411.08832","title":"Offline Adaptation of Quadruped Locomotion using Diffusion Models","created":"2024-11-13","cited_by_count":3,"area":"diffusion"},{"id":"2502.01521","title":"Symmetry-Guided Memory Augmentation for Efficient Locomotion Learning","created":"2025-02-03","cited_by_count":3,"area":"deeprl"},{"id":"2502.07380","title":"Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics","created":"2025-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2505.07321","title":"Drive Fast, Learn Faster: On-Board RL for High Performance Autonomous Racing","created":"2025-05-12","cited_by_count":3,"area":"deeprl"},{"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":"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":"2511.19528","title":"Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories","created":"2025-11-24","cited_by_count":3,"area":"vla"},{"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":"2601.17428","title":"Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement Learning","created":"2026-01-24","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":"2607.28623","title":"PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball","created":"2026-07-30","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":"2412.04273","title":"Reinforcement Learning from Wild Animal Videos","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2502.02921","title":"Robust Reward Alignment via Hypothesis Space Batch Cutting","created":"2025-02-05","cited_by_count":2,"area":"alignment"},{"id":"2503.05035","title":"QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2503.22942","title":"AINav: Large Language Model-Based Adaptive Interactive Navigation","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2506.02507","title":"AURA: Autonomous Upskilling with Retrieval-Augmented Agents","created":"2025-06-03","cited_by_count":2,"area":"rag"},{"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":"2508.21378","title":"RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation","created":"2025-08-29","cited_by_count":2,"area":"lr"},{"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":"2512.15379","title":"Remotely Detectable Robot Policy Watermarking","created":"2025-12-17","cited_by_count":2,"area":null},{"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":"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":"2411.06782","title":"QuadWBG: Generalizable Quadrupedal Whole-Body Grasping","created":"2024-11-11","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":"2503.09985","title":"ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2504.06479","title":"Holistic Fusion: Task- and Setup-Agnostic Robot Localization and State Estimation with Factor Graphs","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2504.08604","title":"Neural Fidelity Calibration for Informative Sim-to-Real Adaptation","created":"2025-04-11","cited_by_count":1,"area":"diffusion"},{"id":"2505.10973","title":"GRoQ-LoCO: Generalist and Robot-agnostic Quadruped Locomotion Control using Offline Datasets","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2507.18992","title":"Reinforcement Learning via Conservative Agent for Environments with Random Delays","created":"2025-07-25","cited_by_count":1,"area":"deeprl"},{"id":"2508.20661","title":"Physics-Guided Residual Reinforcement Learning for Humanoid Narrow-Path Traversal","created":"2025-08-28","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":"2510.04234","title":"Flexible Locomotion Learning with Diffusion Model Predictive Control","created":"2025-10-05","cited_by_count":1,"area":"diffusion"},{"id":"2510.13488","title":"Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations","created":"2025-10-15","cited_by_count":1,"area":"deeprl"},{"id":"2601.15995","title":"PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2602.03087","title":"Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach","created":"2026-02-03","cited_by_count":1,"area":"deeprl"},{"id":"2602.06219","title":"Coupled Local and Global World Models for Efficient First Order RL","created":"2026-02-05","cited_by_count":1,"area":"wm"},{"id":"2602.11143","title":"APEX: Learning Adaptive High-Platform Traversal for Humanoid Robots","created":"2026-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2604.01708","title":"OpenGo: An OpenClaw-Based Robotic Dog with Real-Time Skill Switching","created":"2026-04-02","cited_by_count":1,"area":null}],"next_cursor":"100"}