{"total":413,"rows":[{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458,"area":"wm"},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95,"area":null},{"id":"2412.14058","title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","created":"2024-12-18","cited_by_count":89,"area":"mllm"},{"id":"2506.00613","title":"WorldGym: World Model as An Environment for Policy Evaluation","created":"2025-05-31","cited_by_count":64,"area":"wm"},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60,"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":"2409.16578","title":"FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning","created":"2024-09-25","cited_by_count":54,"area":"deeprl"},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54,"area":"agents"},{"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":"2411.11839","title":"RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator","created":"2024-11-18","cited_by_count":53,"area":null},{"id":"2410.03645","title":"GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs","created":"2024-10-04","cited_by_count":52,"area":"wm"},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51,"area":"offlinerl"},{"id":"2409.12894","title":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","created":"2024-09-19","cited_by_count":45,"area":"vla"},{"id":"2407.20242","title":"BadRobot: Jailbreaking Embodied LLM Agents in the Physical World","created":"2024-07-16","cited_by_count":43,"area":"agents"},{"id":"2402.02511","title":"PoCo: Policy Composition from and for Heterogeneous Robot Learning","created":"2024-02-04","cited_by_count":42,"area":null},{"id":"2310.16029","title":"Finetuning Offline World Models in the Real World","created":"2023-10-24","cited_by_count":41,"area":"wm"},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38,"area":"distill"},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2308.14284","title":"Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning","created":"2023-08-28","cited_by_count":36,"area":null},{"id":"2110.15245","title":"From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence","created":"2021-10-28","cited_by_count":35,"area":null},{"id":"2509.19080","title":"World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation","created":"2025-09-23","cited_by_count":35,"area":"wm"},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2201.12427","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2212.11498","title":"Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers","created":"2022-12-22","cited_by_count":30,"area":null},{"id":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2306.01872","title":"Probabilistic Adaptation of Text-to-Video Models","created":"2023-06-02","cited_by_count":29,"area":"wm"},{"id":"2202.09514","title":"Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training","created":"2022-02-19","cited_by_count":28,"area":null},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","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":"2602.02454","title":"World-Gymnast: Training Robots with Reinforcement Learning in a World Model","created":"2026-02-02","cited_by_count":27,"area":"wm"},{"id":"2210.10691","title":"Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes","created":"2022-10-19","cited_by_count":26,"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":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2402.15399","title":"Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation","created":"2024-02-23","cited_by_count":25,"area":"deeprl"},{"id":"2302.14332","title":"Markerless Camera-to-Robot Pose Estimation via Self-supervised Sim-to-Real Transfer","created":"2023-02-28","cited_by_count":24,"area":null},{"id":"2204.03376","title":"Offline Reinforcement Learning for Safer Blood Glucose Control in People with Type 1 Diabetes","created":"2022-04-07","cited_by_count":23,"area":"offlinerl"},{"id":"2410.14972","title":"MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning","created":"2024-10-19","cited_by_count":23,"area":"moe"},{"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":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2303.04926","title":"Automated Cyber Defence: A Review","created":"2023-03-08","cited_by_count":21,"area":null},{"id":"2307.00014","title":"Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions","created":"2023-06-22","cited_by_count":21,"area":null},{"id":"2503.05833","title":"Refined Policy Distillation: From VLA Generalists to RL Experts","created":"2025-03-06","cited_by_count":21,"area":"vla"},{"id":"2310.16686","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2201.08434","title":"DROPO: Sim-to-Real Transfer with Offline Domain Randomization","created":"2022-01-20","cited_by_count":19,"area":null},{"id":"2304.14329","title":"Learning to Extrapolate: A Transductive Approach","created":"2023-04-27","cited_by_count":19,"area":null},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19,"area":null},{"id":"2311.03622","title":"TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer","created":"2023-11-07","cited_by_count":19,"area":"wm"},{"id":"2405.03666","title":"ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projection","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2406.03704","title":"Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking","created":"2024-06-06","cited_by_count":19,"area":"deeprl"},{"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":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"2405.13178","title":"One-Shot Imitation Learning with Invariance Matching for Robotic Manipulation","created":"2024-05-21","cited_by_count":18,"area":"offlinerl"},{"id":"2502.08449","title":"CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World","created":"2025-02-12","cited_by_count":18,"area":null},{"id":"2203.11653","title":"Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real","created":"2022-03-22","cited_by_count":17,"area":"driving"},{"id":"2603.11653","title":"Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning","created":"2026-03-12","cited_by_count":17,"area":"vla"},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"id":"2205.07229","title":"RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states","created":"2022-05-15","cited_by_count":16,"area":null},{"id":"2211.10649","title":"LibSignal: An Open Library for Traffic Signal Control","created":"2022-11-19","cited_by_count":16,"area":null},{"id":"2301.05033","title":"Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly","created":"2023-01-12","cited_by_count":16,"area":null},{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"id":"2509.18644","title":"Do You Need Proprioceptive States in Visuomotor Policies?","created":"2025-09-23","cited_by_count":16,"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":"2110.12997","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","created":"2021-10-25","cited_by_count":15,"area":null},{"id":"2111.06978","title":"RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN","created":"2021-11-12","cited_by_count":15,"area":null},{"id":"2405.05439","title":"How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation","created":"2024-05-08","cited_by_count":15,"area":"offlinerl"},{"id":"2511.02097","title":"A Step Toward World Models: A Survey on Robotic Manipulation","created":"2025-10-31","cited_by_count":15,"area":"wm"},{"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":"2212.07740","title":"Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer","created":"2022-12-15","cited_by_count":14,"area":null},{"id":"2312.04670","title":"Rapid Motor Adaptation for Robotic Manipulator Arms","created":"2023-12-07","cited_by_count":14,"area":null},{"id":"2506.13762","title":"Touch begins where vision ends: Generalizable policies for contact-rich manipulation","created":"2025-06-16","cited_by_count":14,"area":"offlinerl"},{"id":"2307.08082","title":"POMDP inference and robust solution via deep reinforcement learning: An application to railway optimal maintenance","created":"2023-07-16","cited_by_count":13,"area":null},{"id":"2403.19839","title":"The New Agronomists: Language Models are Experts in Crop Management","created":"2024-03-28","cited_by_count":13,"area":null},{"id":"2205.06676","title":"VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation","created":"2022-05-10","cited_by_count":12,"area":null},{"id":"2404.07988","title":"QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer","created":"2024-04-11","cited_by_count":12,"area":null},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2507.22028","title":"From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning","created":"2025-07-29","cited_by_count":12,"area":null},{"id":"2508.10316","title":"Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances","created":"2025-08-14","cited_by_count":12,"area":"deeprl"},{"id":"2112.12490","title":"Curriculum Learning for Safe Mapless Navigation","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2206.09603","title":"Constrained Reinforcement Learning for Robotics via Scenario-Based Programming","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11,"area":null},{"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":"2105.14218","title":"A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles","created":"2021-05-29","cited_by_count":10,"area":"driving"},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2210.12301","title":"Continual Vision-based Reinforcement Learning with Group Symmetries","created":"2022-10-21","cited_by_count":10,"area":null},{"id":"2305.18464","title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2405.04714","title":"RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes","created":"2024-05-07","cited_by_count":10,"area":"driving"},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2202.06003","title":"Robust Learning from Observation with Model Misspecification","created":"2022-02-12","cited_by_count":9,"area":"offlinerl"},{"id":"2206.11996","title":"The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality","created":"2022-06-23","cited_by_count":9,"area":null},{"id":"2208.02447","title":"DL-DRL: A double-level deep reinforcement learning approach for large-scale task scheduling of multi-UAV","created":"2022-08-04","cited_by_count":9,"area":null},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2211.02201","title":"Learning Tool Morphology for Contact-Rich Manipulation Tasks with Differentiable Simulation","created":"2022-11-04","cited_by_count":9,"area":null},{"id":"2304.03545","title":"AI Model Disgorgement: Methods and Choices","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2305.07958","title":"More for Less: Safe Policy Improvement With Stronger Performance Guarantees","created":"2023-05-13","cited_by_count":9,"area":"offlinerl"}],"next_cursor":"100"}