{"total":78,"rows":[{"id":"2507.21053","title":"Flow Matching Policy Gradients","created":"2025-07-28","cited_by_count":99,"area":"diffusion"},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82,"area":"wm"},{"id":"2607.00272","title":"ASPIRE: Agentic /Skills Discovery for Robotics","created":"2026-06-30","cited_by_count":53,"area":"agents"},{"id":"2509.10771","title":"RSL-RL: A Learning Library for Robotics Research","created":"2025-09-13","cited_by_count":49,"area":"deeprl"},{"id":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44,"area":"deeprl"},{"id":"2502.12152","title":"Learning Getting-Up Policies for Real-World Humanoid Robots","created":"2025-02-17","cited_by_count":26,"area":null},{"id":"2506.10968","title":"Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop","created":"2025-06-12","cited_by_count":25,"area":null},{"id":"2507.22885","title":"Viser: Imperative, Web-based 3D Visualization in Python","created":"2025-07-30","cited_by_count":23,"area":null},{"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":"2510.20813","title":"GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation","created":"2025-10-23","cited_by_count":19,"area":null},{"id":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"area":"deeprl"},{"id":"2602.02481","title":"Flow Policy Gradients for Robot Control","created":"2026-02-02","cited_by_count":16,"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":"2507.00833","title":"HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning","created":"2025-07-01","cited_by_count":13,"area":"lr"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2507.04452","title":"SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training","created":"2025-07-06","cited_by_count":5,"area":"deeprl"},{"id":"2509.16434","title":"End-to-end RL Improves Dexterous Grasping Policies","created":"2025-09-19","cited_by_count":5,"area":null},{"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":"2604.13645","title":"A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies","created":"2026-04-15","cited_by_count":5,"area":null},{"id":"2603.20147","title":"AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning","created":"2026-03-20","cited_by_count":4,"area":"deeprl"},{"id":"2607.26055","title":"$\\pi\\mathbf{R}^2$: Reactive Real-time Flow Policies","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2505.09029","title":"Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control","created":"2025-05-13","cited_by_count":3,"area":"deeprl"},{"id":"2506.15132","title":"Booster Gym: An End-to-End Reinforcement Learning Framework for Humanoid Robot Locomotion","created":"2025-06-18","cited_by_count":3,"area":"deeprl"},{"id":"2602.20220","title":"What Matters for Simulation to Online Reinforcement Learning on Real Robots","created":"2026-02-23","cited_by_count":3,"area":"deeprl"},{"id":"2603.11101","title":"Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure","created":"2026-03-11","cited_by_count":3,"area":null},{"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":"2504.16738","title":"MOSAIC: Skill-Centric Manipulation Planning with Physics Simulation","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2505.18347","title":"The Cell Must Go On: Agar.io for Continual Reinforcement Learning","created":"2025-05-23","cited_by_count":2,"area":"deeprl"},{"id":"2510.11542","title":"NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning","created":"2025-10-13","cited_by_count":2,"area":"deeprl"},{"id":"2512.10117","title":"CHyLL: Learning Continuous Neural Representations of Hybrid Systems","created":"2025-12-10","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":"2603.09237","title":"MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics","created":"2026-03-10","cited_by_count":2,"area":"deeprl"},{"id":"2606.20376","title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","created":"2026-06-18","cited_by_count":2,"area":"deeprl"},{"id":"2607.00442","title":"Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications","created":"2026-07-01","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":"2505.18417","title":"Reinforcement Learning for Ballbot Navigation in Uneven Terrain","created":"2025-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2510.00154","title":"RoboPilot: Generalizable Dynamic Robotic Manipulation with Dual-thinking Modes","created":"2025-09-30","cited_by_count":1,"area":"lr"},{"id":"2510.23176","title":"TARC: Time-Adaptive Robotic Control","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.21363","title":"Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.12612","title":"FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2603.15084","title":"HALO:Closing Sim-to-Real Gap for Heavy-loaded Humanoid Agile Motion Skills via Differentiable Simulation","created":"2026-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2604.02260","title":"Model-Based Reinforcement Learning for Control under Time-Varying Dynamics","created":"2026-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2606.18594","title":"Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation","created":"2026-06-17","cited_by_count":1,"area":"deeprl"},{"id":"2606.29201","title":"Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2503.05146","title":"Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots","created":"2025-03-07","cited_by_count":0,"area":"deeprl"},{"id":"2506.01568","title":"Trajectory First: A Curriculum for Discovering Diverse Policies","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.04646","title":"ActivePusher: Active Learning and Planning with Residual Physics for Nonprehensile Manipulation","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2508.01082","title":"Learning Pivoting Manipulation with Force and Vision Feedback Using Optimization-based Demonstrations","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.18348","title":"PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion","created":"2025-10-21","cited_by_count":0,"area":"deeprl"},{"id":"2511.21169","title":"Kinematics-Aware Multi-Policy Reinforcement Learning for Force-Capable Humanoid Loco-Manipulation","created":"2025-11-26","cited_by_count":0,"area":"deeprl"},{"id":"2601.01288","title":"PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS","created":"2026-01-03","cited_by_count":0,"area":"deeprl"},{"id":"2601.14232","title":"KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.19406","title":"Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.15245","title":"MyoInteract: A Framework for Fast Prototyping of Biomechanical HCI Tasks using Reinforcement Learning","created":"2026-02-16","cited_by_count":0,"area":"deeprl"},{"id":"2603.10878","title":"RL-Augmented MPC for Non-Gaited Legged and Hybrid Locomotion","created":"2026-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2603.21621","title":"Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schr\\\"odinger Bridge","created":"2026-03-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.24047","title":"PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning","created":"2026-03-25","cited_by_count":0,"area":"deeprl"},{"id":"2604.04138","title":"Learning Dexterous Grasping from Sparse Taxonomy Guidance","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2605.24975","title":"Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2605.29564","title":"VE2VF: Vision-Enabled to Vision-Free Distillation via Real-world Reinforcement Learning for Robust Contact-Rich Manipulation","created":"2026-05-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.31481","title":"Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.02636","title":"Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.04569","title":"MineXplore: An Open-Source Reinforcement Learning Exploration Benchmark for GNSS-Denied Underground Environment","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.06218","title":"TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.21387","title":"Long-Distance Real-World Navigation of the Legged-Wheeled Robot Go2-W Using Deep Reinforcement Learning","created":"2026-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.22145","title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","created":"2026-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.17326","title":"Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints","created":"2026-07-19","cited_by_count":0,"area":"deeprl"},{"id":"2608.02433","title":"Foundations of Reinforcement Learning and Control:Connections and New Perspectives","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2608.07870","title":"V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control","created":"2026-08-08","cited_by_count":0,"area":"deeprl"},{"id":"2608.26571","title":"Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.07111","title":"From LLM-Generated Specifications to Learned Quadruped Locomotion","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.32665","title":"Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL","created":"2026-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2609.35525","title":"Deep Epistemic Value Functions for Optimistic Exploration","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.38873","title":"DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.05331","title":"VAMPS: Visual and Motor Policies from Sampling-Based Planning","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.06019","title":"Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.20318","title":"Efficient Test-Time Adaptation For Robot Policies","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}