{"total":168,"rows":[{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"area":"alignment"},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211,"area":"vla"},{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164,"area":null},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149,"area":null},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145,"area":"offlinerl"},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144,"area":"offlinerl"},{"id":"2402.16796","title":"Expressive Whole-Body Control for Humanoid Robots","created":"2024-02-26","cited_by_count":139,"area":null},{"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":"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":"2210.10044","title":"Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion","created":"2022-10-18","cited_by_count":121,"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":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90,"area":null},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83,"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":"2509.19301","title":"Residual Off-Policy RL for Finetuning Behavior Cloning Policies","created":"2025-09-23","cited_by_count":55,"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":"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":"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":"2209.05309","title":"GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots","created":"2022-09-12","cited_by_count":48,"area":null},{"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":"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":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44,"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":"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":"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":"2504.12609","title":"Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration","created":"2025-04-17","cited_by_count":34,"area":null},{"id":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2403.14864","title":"Learning Quadruped Locomotion Using Differentiable Simulation","created":"2024-03-21","cited_by_count":32,"area":null},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2406.12505","title":"Demonstrating Agile Flight from Pixels without State Estimation","created":"2024-06-18","cited_by_count":31,"area":"deeprl"},{"id":"2206.14349","title":"Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision","created":"2022-06-29","cited_by_count":30,"area":null},{"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":"2405.10830","title":"CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion","created":"2024-05-17","cited_by_count":25,"area":"deeprl"},{"id":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24,"area":null},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24,"area":null},{"id":"2210.04435","title":"Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning","created":"2022-10-10","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":"2405.01402","title":"Learning Force Control for Legged Manipulation","created":"2024-05-02","cited_by_count":21,"area":null},{"id":"2310.10486","title":"ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots","created":"2023-10-16","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":"2303.03724","title":"Learning Bipedal Walking for Humanoids with Current Feedback","created":"2023-03-07","cited_by_count":18,"area":null},{"id":"2310.19797","title":"DEFT: Dexterous Fine-Tuning for Real-World Hand Policies","created":"2023-10-30","cited_by_count":17,"area":null},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17,"area":null},{"id":"2405.00846","title":"Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination","created":"2024-05-01","cited_by_count":16,"area":null},{"id":"2406.16087","title":"Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy","created":"2024-06-23","cited_by_count":16,"area":"offlinerl"},{"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":"2407.02666","title":"Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models","created":"2024-07-02","cited_by_count":15,"area":"lr"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","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":"2409.13678","title":"SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience","created":"2024-09-20","cited_by_count":14,"area":"deeprl"},{"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":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2210.03104","title":"Distributionally Adaptive Meta Reinforcement Learning","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11,"area":null},{"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":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","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":"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":"2403.03848","title":"Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning","created":"2024-03-06","cited_by_count":9,"area":"deeprl"},{"id":"2407.07884","title":"Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation","created":"2024-07-10","cited_by_count":9,"area":null},{"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":"2304.08663","title":"Continuous Versatile Jumping Using Learned Action Residuals","created":"2023-04-17","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":"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":"2509.17053","title":"FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Tasks","created":"2025-09-21","cited_by_count":7,"area":"offlinerl"},{"id":"2306.17101","title":"Identifying Important Sensory Feedback for Learning Locomotion Skills","created":"2023-06-29","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":"2409.16611","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":"2410.00120","title":"Learning to Swim: Reinforcement Learning for 6-DOF Control of Thruster-driven Autonomous Underwater Vehicles","created":"2024-09-30","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":"2508.08982","title":"Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion","created":"2025-08-12","cited_by_count":6,"area":null},{"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":"2503.20839","title":"TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion","created":"2025-03-26","cited_by_count":5,"area":"distill"},{"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":"2307.16676","title":"End-to-End Reinforcement Learning for Torque Based Variable Height Hopping","created":"2023-07-31","cited_by_count":3,"area":null},{"id":"2312.05332","title":"MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control","created":"2023-12-08","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":"2412.04323","title":"GRAM: Generalization in Deep RL with a Robust Adaptation Module","created":"2024-12-05","cited_by_count":3,"area":"deeprl"},{"id":"2501.16590","title":"Benchmarking Model Predictive Control and Reinforcement Learning Based Control for Legged Robot Locomotion in MuJoCo Simulation","created":"2025-01-28","cited_by_count":3,"area":"deeprl"},{"id":"2508.11849","title":"LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mamba","created":"2025-08-16","cited_by_count":3,"area":"ssm"},{"id":"2511.21011","title":"Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning","created":"2025-11-26","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"}],"next_cursor":"100"}