{"total":113,"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":"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":"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":"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":"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":"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":"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":"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":"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":"2311.13081","title":"Learning to Fly in Seconds","created":"2023-11-22","cited_by_count":31,"area":null},{"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":"2405.14853","title":"Privileged Sensing Scaffolds Reinforcement Learning","created":"2024-05-23","cited_by_count":19,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"2210.00350","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2304.05008","title":"Habits and goals in synergy: a variational Bayesian framework for behavior","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2511.10635","title":"Robot Crash Course: Learning Soft and Stylized Falling","created":"2025-11-13","cited_by_count":4,"area":null},{"id":"2102.08581","title":"Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning","created":"2021-02-17","cited_by_count":3,"area":null},{"id":"2102.11893","title":"Honey, I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2104.10986","title":"Reinforcement Learning using Guided Observability","created":"2021-04-22","cited_by_count":3,"area":null},{"id":"2402.09387","title":"Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning","created":"2024-02-14","cited_by_count":3,"area":null},{"id":"2506.16079","title":"Investigating Lagrangian Neural Networks for Infinite Horizon Planning in Quadrupedal Locomotion","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2507.18059","title":"Multi-Agent Guided Policy Optimization","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2508.11929","title":"No More Blind Spots: Learning Vision-Based Omnidirectional Bipedal Locomotion for Challenging Terrain","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2104.14386","title":"Pre-training of Deep RL Agents for Improved Learning under Domain Randomization","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2203.05985","title":"Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control","created":"2022-03-11","cited_by_count":2,"area":null},{"id":"2206.14847","title":"Deep Reinforcement Learning for Small Bowel Path Tracking using Different Types of Annotations","created":"2022-06-29","cited_by_count":2,"area":null},{"id":"2207.01840","title":"Randomized-to-Canonical Model Predictive Control for Real-world Visual Robotic Manipulation","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2304.12330","title":"Parallel bootstrap-based on-policy deep reinforcement learning for continuous flow control applications","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2601.09605","title":"Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2103.11881","title":"Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recovery","created":"2021-03-22","cited_by_count":1,"area":null},{"id":"2106.13037","title":"Mix and Mask Actor-Critic Methods","created":"2021-06-24","cited_by_count":1,"area":null},{"id":"2204.08573","title":"Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models","created":"2022-04-18","cited_by_count":1,"area":null},{"id":"2208.02376","title":"AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2305.11107","title":"From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2309.13365","title":"Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2401.09258","title":"Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2411.06782","title":"QuadWBG: Generalizable Quadrupedal Whole-Body Grasping","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2507.23015","title":"Learning to Prune Branches in Modern Tree-Fruit Orchards","created":"2025-07-30","cited_by_count":1,"area":null},{"id":"2510.14947","title":"Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotion","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2510.23176","title":"TARC: Time-Adaptive Robotic Control","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.15995","title":"PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2604.25554","title":"Egocentric Tactile and Proximity Sensors as Observation Priors for Humanoid Collision Avoidance","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2606.08253","title":"Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2608.16739","title":"Le Critique: Privileged Value Functions for LLM Reinforcement Learning","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2109.08677","title":"Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2206.00518","title":"Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning","created":"2022-06-01","cited_by_count":0,"area":null},{"id":"2301.08030","title":"Multi-Agent Interplay in a Competitive Survival Environment","created":"2023-01-19","cited_by_count":0,"area":null},{"id":"2301.13343","title":"Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2304.05839","title":"Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2306.08762","title":"Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2306.15793","title":"A Population-Level Analysis of Neural Dynamics in Robust Legged Robots","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2307.12983","title":"Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation","created":"2023-07-24","cited_by_count":0,"area":null},{"id":"2310.05430","title":"Replication of Multi-agent Reinforcement Learning for the \"Hide and Seek\" Problem","created":"2023-10-09","cited_by_count":0,"area":null}],"next_cursor":"100"}