{"total":123,"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":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2304.05015","title":"Continual Semantic Segmentation with Automatic Memory Sample Selection","created":"2023-04-11","cited_by_count":39,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2108.13035","title":"SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning","created":"2021-08-30","cited_by_count":31,"area":null},{"id":"2202.10583","title":"MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned","created":"2022-02-17","cited_by_count":26,"area":null},{"id":"2201.00042","title":"Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24,"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":"2302.09772","title":"Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot","created":"2023-02-20","cited_by_count":23,"area":null},{"id":"2203.04051","title":"Robot Learning of Mobile Manipulation with Reachability Behavior Priors","created":"2022-03-08","cited_by_count":22,"area":null},{"id":"2311.02379","title":"Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models","created":"2023-11-04","cited_by_count":22,"area":null},{"id":"2106.01854","title":"Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning","created":"2021-06-03","cited_by_count":21,"area":null},{"id":"2107.09822","title":"Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics","created":"2021-07-21","cited_by_count":20,"area":null},{"id":"2204.05369","title":"Learning Implicit Priors for Motion Optimization","created":"2022-04-11","cited_by_count":20,"area":null},{"id":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2106.08796","title":"Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2402.13820","title":"FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning","created":"2024-02-21","cited_by_count":18,"area":null},{"id":"2209.13308","title":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","created":"2022-09-27","cited_by_count":17,"area":null},{"id":"2411.01813","title":"So You Think You Can Scale Up Autonomous Robot Data Collection?","created":"2024-11-04","cited_by_count":17,"area":null},{"id":"2302.13137","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","created":"2023-02-25","cited_by_count":15,"area":null},{"id":"2401.00678","title":"General-purpose foundation models for increased autonomy in robot-assisted surgery","created":"2024-01-01","cited_by_count":15,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2502.03350","title":"Optimal Task Order for Continual Learning of Multiple Tasks","created":"2025-02-05","cited_by_count":14,"area":null},{"id":"2301.00452","title":"Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning","created":"2023-01-01","cited_by_count":13,"area":null},{"id":"2406.07145","title":"Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2303.05344","title":"Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective","created":"2023-03-09","cited_by_count":10,"area":null},{"id":"2304.04602","title":"Learning a Universal Human Prior for Dexterous Manipulation from Human Preference","created":"2023-04-10","cited_by_count":10,"area":null},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10,"area":null},{"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":"2110.04003","title":"Learning to Centralize Dual-Arm Assembly","created":"2021-10-08","cited_by_count":9,"area":null},{"id":"2306.11918","title":"Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2307.16503","title":"Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot","created":"2023-07-31","cited_by_count":9,"area":null},{"id":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"area":null},{"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":"2112.03575","title":"MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance","created":"2021-12-07","cited_by_count":8,"area":null},{"id":"2305.10411","title":"Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2309.09752","title":"Contrastive Initial State Buffer for Reinforcement Learning","created":"2023-09-18","cited_by_count":8,"area":null},{"id":"2406.19963","title":"Text2Robot: Evolutionary Robot Design from Text Descriptions","created":"2024-06-28","cited_by_count":8,"area":null},{"id":"2504.04612","title":"Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use","created":"2025-04-06","cited_by_count":8,"area":null},{"id":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2407.05966","title":"On Bellman equations for continuous-time policy evaluation I: discretization and approximation","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2507.19975","title":"A roadmap for AI in robotics","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2206.15086","title":"Colonoscopy Navigation using End-to-End Deep Visuomotor Control: A User Study","created":"2022-06-30","cited_by_count":6,"area":null},{"id":"2211.06407","title":"Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2306.17101","title":"Identifying Important Sensory Feedback for Learning Locomotion Skills","created":"2023-06-29","cited_by_count":6,"area":null},{"id":"2406.03641","title":"Task and Motion Planning for Execution in the Real","created":"2024-06-05","cited_by_count":6,"area":null},{"id":"2106.15775","title":"Koopman Spectrum Nonlinear Regulators and Efficient Online Learning","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2203.02230","title":"Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2209.11275","title":"Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learning","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2212.14720","title":"Learning from Data Streams: An Overview and Update","created":"2022-12-30","cited_by_count":5,"area":null},{"id":"2308.12772","title":"Intentionally-underestimated Value Function at Terminal State for Temporal-difference Learning with Mis-designed Reward","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2309.14727","title":"Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization","created":"2023-09-26","cited_by_count":5,"area":null},{"id":"2103.03793","title":"Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors","created":"2021-03-05","cited_by_count":4,"area":null},{"id":"2111.03915","title":"Robust Deep Reinforcement Learning for Quadcopter Control","created":"2021-11-06","cited_by_count":4,"area":null},{"id":"2210.00140","title":"Efficiently Learning Small Policies for Locomotion and Manipulation","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2302.13191","title":"DeepCPG Policies for Robot Locomotion","created":"2023-02-25","cited_by_count":4,"area":null},{"id":"2411.14246","title":"Simulation-Aided Policy Tuning for Black-Box Robot Learning","created":"2024-11-21","cited_by_count":4,"area":null},{"id":"2108.09895","title":"Burst Imaging for Light-Constrained Structure-From-Motion","created":"2021-08-23","cited_by_count":3,"area":null},{"id":"2201.05599","title":"Smart Magnetic Microrobots Learn to Swim with Deep Reinforcement Learning","created":"2022-01-14","cited_by_count":3,"area":null},{"id":"2205.08441","title":"Conditional Visual Servoing for Multi-Step Tasks","created":"2022-05-17","cited_by_count":3,"area":null},{"id":"2210.08065","title":"Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2312.15965","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2404.16388","title":"SwarmRL: Building the Future of Smart Active Systems","created":"2024-04-25","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2111.02371","title":"What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2306.07408","title":"Robust Reinforcement Learning through Efficient Adversarial Herding","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2306.12314","title":"Introspective Action Advising for Interpretable Transfer Learning","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2307.16769","title":"2-Level Reinforcement Learning for Ships on Inland Waterways: Path Planning and Following","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2312.15160","title":"Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning","created":"2023-12-23","cited_by_count":2,"area":null},{"id":"2403.14049","title":"A Roadmap Towards Automated and Regulated Robotic Systems","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2409.05898","title":"Simplex-enabled Safe Continual Learning Machine","created":"2024-09-05","cited_by_count":2,"area":null},{"id":"2410.09134","title":"Multi-Agent Actor-Critics in Autonomous Cyber Defense","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2410.12172","title":"The State of Robot Motion Generation","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2503.15685","title":"Robotic Paper Wrapping by Learning Force Control","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2510.27428","title":"Learning Soft Robotic Dynamics with Active Exploration","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2106.13970","title":"Intrinsically Motivated Self-supervised Learning in Reinforcement Learning","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2112.05299","title":"Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2209.14488","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2210.05187","title":"Broad-persistent Advice for Interactive Reinforcement Learning Scenarios","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2304.04911","title":"Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2305.10171","title":"Goal-Conditioned Supervised Learning with Sub-Goal Prediction","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2306.04299","title":"Timing Process Interventions with Causal Inference and Reinforcement Learning","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2306.08224","title":"Expanding Versatility of Agile Locomotion through Policy Transitions Using Latent State Representation","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2310.15059","title":"Robot Skill Generalization via Keypoint Integrated Soft Actor-Critic Gaussian Mixture Models","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2311.15960","title":"Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2312.05991","title":"Modifying RL Policies with Imagined Actions: How Predictable Policies Can Enable Users to Perform Novel Tasks","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2402.09113","title":"How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2405.07515","title":"OpenBot-Fleet: A System for Collective Learning with Real Robots","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2203.10351","title":"The Sandbox Environment for Generalizable Agent Research (SEGAR)","created":"2022-03-19","cited_by_count":0,"area":null},{"id":"2203.14905","title":"Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2204.12707","title":"Accelerated Continuous-Time Approximate Dynamic Programming via Data-Assisted Hybrid Control","created":"2022-04-27","cited_by_count":0,"area":null},{"id":"2208.00525","title":"Learning to generate Reliable Broadcast Algorithms","created":"2022-07-31","cited_by_count":0,"area":null},{"id":"2209.04999","title":"Multi-Step First: A Lightweight Deep Reinforcement Learning Strategy for Robust Continuous Control with Partial Observability","created":"2022-09-12","cited_by_count":0,"area":null}],"next_cursor":"100"}