{"total":63,"rows":[{"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":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"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":"2203.06481","title":"GATSBI: Generative Adversarial Training for Simulation-Based Inference","created":"2022-03-12","cited_by_count":36,"area":null},{"id":"2201.08355","title":"Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees","created":"2022-01-20","cited_by_count":27,"area":null},{"id":"2409.15250","title":"ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models","created":"2024-09-23","cited_by_count":27,"area":null},{"id":"2312.03673","title":"On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer","created":"2023-12-06","cited_by_count":26,"area":null},{"id":"2510.20808","title":"The Reality Gap in Robotics: Challenges, Solutions, and Best Practices","created":"2025-10-23","cited_by_count":24,"area":null},{"id":"2503.14526","title":"ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis","created":"2025-03-15","cited_by_count":22,"area":"vla"},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19,"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":"2311.18044","title":"Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges","created":"2023-11-29","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":"2506.03079","title":"ORV: 4D Occupancy-centric Robot Video Generation","created":"2025-06-03","cited_by_count":17,"area":"wm"},{"id":"2411.01775","title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","created":"2024-11-04","cited_by_count":16,"area":null},{"id":"2206.06282","title":"Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks","created":"2022-06-13","cited_by_count":14,"area":null},{"id":"2211.14655","title":"How Crucial is Transformer in Decision Transformer?","created":"2022-11-26","cited_by_count":14,"area":"offlinerl"},{"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":"2310.04517","title":"Domain Randomization for Sim2real Transfer of Automatically Generated Grasping Datasets","created":"2023-10-06","cited_by_count":9,"area":null},{"id":"2403.12193","title":"Continual Domain Randomization","created":"2024-03-18","cited_by_count":8,"area":"deeprl"},{"id":"2604.02523","title":"Tune to Learn: How Controller Gains Shape Robot Policy Learning","created":"2026-04-02","cited_by_count":8,"area":"deeprl"},{"id":"2302.11694","title":"Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control","created":"2023-02-22","cited_by_count":5,"area":null},{"id":"2410.03920","title":"Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2503.24371","title":"Policy Gradient for LQR with Domain Randomization","created":"2025-03-31","cited_by_count":5,"area":"deeprl"},{"id":"2206.14661","title":"Online vs. Offline Adaptive Domain Randomization Benchmark","created":"2022-06-29","cited_by_count":4,"area":null},{"id":"2207.03456","title":"Stochastic optimal well control in subsurface reservoirs using reinforcement learning","created":"2022-07-07","cited_by_count":4,"area":null},{"id":"2503.08306","title":"Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2510.22757","title":"Distributionally Robust Optimization via Diffusion Ambiguity Modeling","created":"2025-10-26","cited_by_count":4,"area":null},{"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":"2601.18923","title":"DeFM: Learning Foundation Representations from Depth for Robotics","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2602.08976","title":"Distributionally Robust Optimization via Generative Ambiguity Modeling","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2303.02234","title":"Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2303.04136","title":"Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2503.10949","title":"Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics","created":"2025-03-13","cited_by_count":2,"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":"2504.15414","title":"Post-Convergence Sim-to-Real Policy Transfer: A Principled Alternative to Cherry-Picking","created":"2025-04-21","cited_by_count":1,"area":"deeprl"},{"id":"2507.03068","title":"Mitigating Goal Misgeneralization via Minimax Regret","created":"2025-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2510.25063","title":"Control Synthesis with Reinforcement Learning: A Modeling Perspective","created":"2025-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2604.05484","title":"CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment","created":"2026-04-07","cited_by_count":1,"area":"agents"},{"id":"2202.13638","title":"GPU-Accelerated Policy Optimization via Batch Automatic Differentiation of Gaussian Processes for Real-World Control","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2301.06987","title":"Sim-Anchored Learning for On-the-Fly Adaptation","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2306.14705","title":"Augmenting Control over Exploration Space in Molecular Dynamics Simulators to Streamline De Novo Analysis through Generative Control Policies","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2311.16656","title":"Pseudo-Likelihood Inference","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2312.05023","title":"Reinforcement Learning-Based Bionic Reflex Control for Anthropomorphic Robotic Grasping exploiting Domain Randomization","created":"2023-12-08","cited_by_count":0,"area":null},{"id":"2412.13224","title":"Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning","created":"2024-12-17","cited_by_count":0,"area":"deeprl"},{"id":"2510.15189","title":"RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation","created":"2025-10-16","cited_by_count":0,"area":"offlinerl"},{"id":"2510.26656","title":"Posterior-driven Heuristic Support Adaptation in a Probabilistic Treatment of Real2Sim2Real for Vision-Driven Deformable Linear Object Manipulation","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2602.06326","title":"Online Adaptive Reinforcement Learning with Echo State Networks for Non-Stationary Dynamics","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2602.15816","title":"Developing AI Agents with Simulated Data: Why, what, and how?","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.18336","title":"ManiDreams: An Open-Source Library for Robust Object Manipulation via Uncertainty-aware Task-specific Intuitive Physics","created":"2026-03-18","cited_by_count":0,"area":"wm"},{"id":"2603.25420","title":"VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents","created":"2026-03-26","cited_by_count":0,"area":"agents"},{"id":"2604.09487","title":"Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks","created":"2026-04-10","cited_by_count":0,"area":null},{"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":"2606.08249","title":"Disturbance-Aware Aerial Robotics for Ethical Wildlife Monitoring","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.18532","title":"AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.22062","title":"How Should a Simulation-to-Reality Transfer Budget Be Spent?","created":"2026-06-20","cited_by_count":0,"area":null},{"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":"2607.11959","title":"Calibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses","created":"2026-07-12","cited_by_count":0,"area":"deeprl"},{"id":"2607.26121","title":"Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.04832","title":"Robust Control under Stationary Ambiguity","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.18111","title":"A Comprehensive Review of Generative Physical Artificial Intelligence","created":"2026-09-16","cited_by_count":0,"area":"diffusion"},{"id":"2610.06400","title":"Visual Swarm Navigation via Deep Reinforcement Learning and Evolutionary Hybrid Design","created":"2026-10-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.16478","title":"XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}