{"total":133,"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":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170,"area":"agents"},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149,"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":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72,"area":null},{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48,"area":"deeprl"},{"id":"2502.08378","title":"Learning Humanoid Standing-up Control across Diverse Postures","created":"2025-02-12","cited_by_count":46,"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":"2402.18294","title":"Whole-body Humanoid Robot Locomotion with Human Reference","created":"2024-02-28","cited_by_count":29,"area":"offlinerl"},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2305.10912","title":"A Generalist Dynamics Model for Control","created":"2023-05-18","cited_by_count":24,"area":"wm"},{"id":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","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":"2409.20568","title":"Continuously Improving Mobile Manipulation with Autonomous Real-World RL","created":"2024-09-30","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":"2409.05864","title":"Neural MP: A Generalist Neural Motion Planner","created":"2024-09-09","cited_by_count":19,"area":null},{"id":"2410.15979","title":"Learning Quadrotor Control From Visual Features Using Differentiable Simulation","created":"2024-10-21","cited_by_count":19,"area":"deeprl"},{"id":"2411.00781","title":"Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies","created":"2024-10-16","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":"2405.02425","title":"Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":17,"area":"deeprl"},{"id":"2412.16346","title":"SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum","created":"2024-12-20","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":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14,"area":null},{"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":"2602.07439","title":"TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control","created":"2026-02-07","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":"2505.00663","title":"Wasserstein Policy Optimization","created":"2025-05-01","cited_by_count":13,"area":"deeprl"},{"id":"2311.15951","title":"Replay across Experiments: A Natural Extension of Off-Policy RL","created":"2023-11-27","cited_by_count":10,"area":null},{"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":"2305.10455","title":"Towards Generalist Robots: A Promising Paradigm via Generative Simulation","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2407.15134","title":"Proximal Policy Distillation","created":"2024-07-21","cited_by_count":9,"area":"distill"},{"id":"2410.13979","title":"RecoveryChaining: Learning Local Recovery Policies for Robust Manipulation","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2510.18002","title":"Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints","created":"2025-10-20","cited_by_count":9,"area":"deeprl"},{"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":"2402.01361","title":"To the Max: Reinventing Reward in Reinforcement Learning","created":"2024-02-02","cited_by_count":8,"area":"deeprl"},{"id":"2508.15755","title":"Neural Robot Dynamics","created":"2025-08-21","cited_by_count":8,"area":null},{"id":"2509.11259","title":"ICR-RL: Deep Reinforcement Learning via In-Context Regression","created":"2025-09-14","cited_by_count":8,"area":null},{"id":"2307.14732","title":"A Strategic Framework for Optimal Decisions in Football 1-vs-1 Shot-Taking Situations: An Integrated Approach of Machine Learning, Theory-Based Modeling, and Game Theory","created":"2023-07-27","cited_by_count":7,"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":"2412.09417","title":"Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer","created":"2024-12-12","cited_by_count":7,"area":"deeprl"},{"id":"2507.19975","title":"A roadmap for AI in robotics","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2508.12252","title":"Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids","created":"2025-08-17","cited_by_count":7,"area":"deeprl"},{"id":"2402.06783","title":"Learn to Teach: Sample-Efficient Privileged Learning for Humanoid Locomotion over Diverse Terrains","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2410.10834","title":"Focus On What Matters: Separated Models For Visual-Based RL Generalization","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"id":"2309.16074","title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning","created":"2023-09-28","cited_by_count":5,"area":"offlinerl"},{"id":"2505.12278","title":"Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning","created":"2025-05-18","cited_by_count":5,"area":"deeprl"},{"id":"2505.19923","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2403.12589","title":"FootstepNet: an Efficient Actor-Critic Method for Fast On-line Bipedal Footstep Planning and Forecasting","created":"2024-03-19","cited_by_count":4,"area":"deeprl"},{"id":"2405.03865","title":"Information-driven Affordance Discovery for Efficient Robotic Manipulation","created":"2024-05-06","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":"2408.14063","title":"Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning","created":"2024-08-26","cited_by_count":4,"area":"deeprl"},{"id":"2412.16244","title":"The impact of behavioral diversity in multi-agent reinforcement learning","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2502.01932","title":"VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play","created":"2025-02-04","cited_by_count":4,"area":"deeprl"},{"id":"2505.06218","title":"Let Humanoids Hike! Integrative Skill Development on Complex Trails","created":"2025-05-09","cited_by_count":4,"area":null},{"id":"2403.14300","title":"DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2409.04467","title":"State and Action Factorization in Power Grids","created":"2024-09-03","cited_by_count":3,"area":"deeprl"},{"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":"2410.01458","title":"From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge","created":"2024-10-02","cited_by_count":3,"area":null},{"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":"2602.16548","title":"RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion","created":"2026-02-18","cited_by_count":3,"area":"diffusion"},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2405.03341","title":"Enhancing Q-Learning with Large Language Model Heuristics","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2405.18300","title":"CompetEvo: Towards Morphological Evolution from Competition","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2406.07877","title":"Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty","created":"2024-06-12","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":"2503.08349","title":"LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures","created":"2025-03-11","cited_by_count":2,"area":"deeprl"},{"id":"2503.22249","title":"FLAM: Foundation Model-Based Body Stabilization for Humanoid Locomotion and Manipulation","created":"2025-03-28","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":"2505.02483","title":"Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning","created":"2025-05-05","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":"2510.22336","title":"Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery","created":"2025-10-25","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":"2601.22024","title":"SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile Networks","created":"2026-01-29","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":"2603.13707","title":"REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning","created":"2026-03-14","cited_by_count":2,"area":"diffusion"},{"id":"2603.28243","title":"Cost-Matching Model Predictive Control for Efficient Reinforcement Learning in Humanoid Locomotion","created":"2026-03-30","cited_by_count":2,"area":"deeprl"},{"id":"2606.06746","title":"Performance Variation in Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2402.16281","title":"RobKiNet: Robotic Kinematics Informed Neural Network for Optimal Robot Configuration Prediction","created":"2024-02-26","cited_by_count":1,"area":null},{"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":"2405.11457","title":"Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice","created":"2024-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2407.18913","title":"SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments","created":"2024-07-26","cited_by_count":1,"area":"deeprl"},{"id":"2410.19564","title":"Robotic Learning in your Backyard: A Neural Simulator from Open Source Components","created":"2024-10-25","cited_by_count":1,"area":"deeprl"},{"id":"2411.05718","title":"A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2503.05092","title":"Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation","created":"2025-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2503.08061","title":"ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2506.16590","title":"Energy-Based Transfer for Reinforcement Learning","created":"2025-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2507.00273","title":"Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation","created":"2025-06-30","cited_by_count":1,"area":"deeprl"},{"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":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","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":"2509.21126","title":"Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning","created":"2025-09-25","cited_by_count":1,"area":"vla"},{"id":"2602.07441","title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","created":"2026-02-07","cited_by_count":1,"area":"offlinerl"},{"id":"2603.07578","title":"Approximate Imitation Learning for Event-based Quadrotor Flight in Cluttered Environments","created":"2026-03-08","cited_by_count":1,"area":"offlinerl"},{"id":"2604.14834","title":"Switch: Learning Agile Skills Switching for Humanoid Robots","created":"2026-04-16","cited_by_count":1,"area":"deeprl"},{"id":"2604.20841","title":"DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.22748","title":"Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.11092","title":"RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning","created":"2026-06-09","cited_by_count":1,"area":"deeprl"},{"id":"2607.16421","title":"When to Plan: Learning to Select Between Reactive Control and Deliberative Planning","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2310.16659","title":"Multi-Agent Reinforcement Learning-Based UAV Pathfinding for Obstacle Avoidance in Stochastic Environment","created":"2023-10-25","cited_by_count":0,"area":null}],"next_cursor":"100"}