{"total":238,"rows":[{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998,"area":null},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149,"area":null},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126,"area":"offlinerl"},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122,"area":null},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118,"area":"lr"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"area":null},{"id":"2511.07820","title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","created":"2025-11-11","cited_by_count":101,"area":null},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"id":"2212.05711","title":"CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning","created":"2022-12-12","cited_by_count":71,"area":"offlinerl"},{"id":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70,"area":null},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"area":null},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60,"area":null},{"id":"2210.06463","title":"Holo-Dex: Teaching Dexterity with Immersive Mixed Reality","created":"2022-10-12","cited_by_count":57,"area":null},{"id":"2212.05749","title":"On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline","created":"2022-12-12","cited_by_count":56,"area":null},{"id":"2408.14472","title":"Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning","created":"2024-08-26","cited_by_count":56,"area":"wm"},{"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":"2104.07662","title":"Auto-Tuned Sim-to-Real Transfer","created":"2021-04-15","cited_by_count":49,"area":null},{"id":"2201.07779","title":"Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation","created":"2022-01-19","cited_by_count":49,"area":null},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","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":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44,"area":"deeprl"},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2403.02338","title":"Twisting Lids Off with Two Hands","created":"2024-03-04","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":"2108.09779","title":"Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger","created":"2021-08-22","cited_by_count":38,"area":null},{"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":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35,"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":"2509.15155","title":"Self-Improving Embodied Foundation Models","created":"2025-09-18","cited_by_count":32,"area":"synth"},{"id":"2311.13081","title":"Learning to Fly in Seconds","created":"2023-11-22","cited_by_count":31,"area":null},{"id":"2403.12203","title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","created":"2024-03-18","cited_by_count":31,"area":"deeprl"},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","cited_by_count":29,"area":null},{"id":"2203.05549","title":"Context is Everything: Implicit Identification for Dynamics Adaptation","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2410.03654","title":"Learning Humanoid Locomotion over Challenging Terrain","created":"2024-10-04","cited_by_count":26,"area":null},{"id":"2105.11674","title":"Unbiased Asymmetric Reinforcement Learning under Partial Observability","created":"2021-05-25","cited_by_count":25,"area":null},{"id":"2406.01633","title":"On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots","created":"2024-06-01","cited_by_count":24,"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":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23,"area":null},{"id":"2109.14549","title":"Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization","created":"2021-09-29","cited_by_count":23,"area":null},{"id":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2207.10148","title":"Learning Deformable Object Manipulation from Expert Demonstrations","created":"2022-07-20","cited_by_count":19,"area":"offlinerl"},{"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":"2405.14853","title":"Privileged Sensing Scaffolds Reinforcement Learning","created":"2024-05-23","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":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18,"area":"offlinerl"},{"id":"2211.01991","title":"Leveraging Fully Observable Policies for Learning under Partial Observability","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2301.13857","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","created":"2023-01-31","cited_by_count":18,"area":null},{"id":"2409.00951","title":"Semantically Controllable Augmentations for Generalizable Robot Learning","created":"2024-09-02","cited_by_count":18,"area":null},{"id":"2409.16784","title":"World Model-based Perception for Visual Legged Locomotion","created":"2024-09-25","cited_by_count":18,"area":"wm"},{"id":"2510.11072","title":"PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System","created":"2025-10-13","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":"2510.14959","title":"CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions","created":"2025-10-16","cited_by_count":17,"area":"deeprl"},{"id":"2406.12563","title":"A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo","created":"2024-06-18","cited_by_count":15,"area":"deeprl"},{"id":"2509.14353","title":"DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion","created":"2025-09-17","cited_by_count":15,"area":"diffusion"},{"id":"2512.03028","title":"SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control","created":"2025-12-02","cited_by_count":15,"area":"offlinerl"},{"id":"2602.16863","title":"SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation","created":"2026-02-18","cited_by_count":15,"area":null},{"id":"2405.17416","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","created":"2024-05-27","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":"2204.01571","title":"Coarse-to-Fine Q-attention with Learned Path Ranking","created":"2022-04-04","cited_by_count":13,"area":null},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2107.00339","title":"Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding","created":"2021-07-01","cited_by_count":12,"area":null},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2409.15780","title":"A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards","created":"2024-09-24","cited_by_count":12,"area":"deeprl"},{"id":"2505.02216","title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","created":"2025-05-04","cited_by_count":12,"area":null},{"id":"2306.06799","title":"On the Efficacy of 3D Point Cloud Reinforcement Learning","created":"2023-06-11","cited_by_count":11,"area":null},{"id":"2306.11488","title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","created":"2023-06-20","cited_by_count":11,"area":"wm"},{"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":"2502.17219","title":"Humanoid Whole-Body Locomotion on Narrow Terrain via Dynamic Balance and Reinforcement Learning","created":"2025-02-24","cited_by_count":11,"area":"deeprl"},{"id":"2506.05997","title":"Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement Learning","created":"2025-06-06","cited_by_count":11,"area":"deeprl"},{"id":"2510.14930","title":"VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning","created":"2025-10-16","cited_by_count":11,"area":"offlinerl"},{"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":"2110.01840","title":"Deep reinforcement learning for guidewire navigation in coronary artery phantom","created":"2021-10-05","cited_by_count":10,"area":null},{"id":"2111.06383","title":"Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation","created":"2021-11-11","cited_by_count":10,"area":"offlinerl"},{"id":"2212.07398","title":"Policy Adaptation from Foundation Model Feedback","created":"2022-12-14","cited_by_count":10,"area":"mllm"},{"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":"2307.01938","title":"Physics-based Motion Retargeting from Sparse Inputs","created":"2023-07-04","cited_by_count":10,"area":null},{"id":"2502.20168","title":"Accelerating Model-Based Reinforcement Learning with State-Space World Models","created":"2025-02-27","cited_by_count":10,"area":"wm"},{"id":"2603.15789","title":"Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning","created":"2026-03-16","cited_by_count":10,"area":"deeprl"},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2204.12471","title":"Coarse-to-fine Q-attention with Tree Expansion","created":"2022-04-26","cited_by_count":9,"area":null},{"id":"2407.07884","title":"Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation","created":"2024-07-10","cited_by_count":9,"area":null},{"id":"2512.02011","title":"Learning Dexterous Manipulation Skills from Imperfect Simulations","created":"2025-12-01","cited_by_count":9,"area":"deeprl"},{"id":"2401.13362","title":"TraKDis: A Transformer-based Knowledge Distillation Approach for Visual Reinforcement Learning with Application to Cloth Manipulation","created":"2024-01-24","cited_by_count":8,"area":"deeprl"},{"id":"2203.00904","title":"Weakly Supervised Correspondence Learning","created":"2022-03-02","cited_by_count":7,"area":null},{"id":"2409.09441","title":"PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion","created":"2024-09-14","cited_by_count":7,"area":null},{"id":"2412.13662","title":"When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?","created":"2024-12-18","cited_by_count":7,"area":"deeprl"},{"id":"2508.02159","title":"PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning","created":"2025-08-04","cited_by_count":7,"area":"wm"},{"id":"2608.06243","title":"DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models","created":"2026-08-06","cited_by_count":7,"area":"lr"},{"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":"2406.04835","title":"SLR: Learning Quadruped Locomotion without Privileged Information","created":"2024-06-07","cited_by_count":6,"area":"deeprl"},{"id":"2412.09149","title":"Student-Informed Teacher Training","created":"2024-12-12","cited_by_count":6,"area":"offlinerl"},{"id":"2501.19116","title":"A Theoretical Justification for Asymmetric Actor-Critic Algorithms","created":"2025-01-31","cited_by_count":6,"area":"deeprl"}],"next_cursor":"100"}