{"total":133,"rows":[{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"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":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2310.07985","title":"Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization","created":"2023-10-12","cited_by_count":142,"area":null},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89,"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":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2101.04882","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","created":"2021-01-13","cited_by_count":72,"area":null},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"id":"2205.03532","title":"Factory: Fast Contact for Robotic Assembly","created":"2022-05-07","cited_by_count":54,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2202.09400","title":"Equivariant Transporter Network","created":"2022-02-18","cited_by_count":46,"area":null},{"id":"2103.08737","title":"Growing 3D Artefacts and Functional Machines with Neural Cellular Automata","created":"2021-03-15","cited_by_count":38,"area":null},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2103.11512","title":"Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study","created":"2021-03-21","cited_by_count":30,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28,"area":null},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2204.13998","title":"Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction","created":"2022-04-03","cited_by_count":24,"area":null},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24,"area":null},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23,"area":null},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","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":"2310.19620","title":"Large Trajectory Models are Scalable Motion Predictors and Planners","created":"2023-10-30","cited_by_count":23,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2205.05212","title":"A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning","created":"2022-05-11","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":"2107.08325","title":"Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning","created":"2021-07-18","cited_by_count":21,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2502.20382","title":"Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization","created":"2025-02-27","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":"2308.07948","title":"Leveraging Symmetries in Pick and Place","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2102.09754","title":"VisuoSpatial Foresight for Physical Sequential Fabric Manipulation","created":"2021-02-19","cited_by_count":18,"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":"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":"2210.07432","title":"Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations","created":"2022-10-14","cited_by_count":14,"area":null},{"id":"2112.00597","title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation","created":"2021-12-01","cited_by_count":13,"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":"2201.12231","title":"Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications","created":"2022-01-28","cited_by_count":12,"area":null},{"id":"2211.06625","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","created":"2022-11-12","cited_by_count":12,"area":null},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2403.06420","title":"RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2509.09671","title":"Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration","created":"2025-09-11","cited_by_count":11,"area":null},{"id":"2104.11106","title":"Formula RL: Deep Reinforcement Learning for Autonomous Racing using Telemetry Data","created":"2021-04-22","cited_by_count":10,"area":null},{"id":"2210.01774","title":"MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization","created":"2022-09-01","cited_by_count":10,"area":null},{"id":"2311.15951","title":"Replay across Experiments: A Natural Extension of Off-Policy RL","created":"2023-11-27","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":"2305.13030","title":"Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2103.05140","title":"Benchmarking Off-The-Shelf Solutions to Robotic Assembly Tasks","created":"2021-03-08","cited_by_count":7,"area":null},{"id":"2201.04286","title":"Evolutionary Action Selection for Gradient-based Policy Learning","created":"2022-01-12","cited_by_count":7,"area":null},{"id":"2210.09337","title":"Robust Imitation of a Few Demonstrations with a Backwards Model","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2210.10464","title":"On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2110.03608","title":"How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents","created":"2021-10-07","cited_by_count":6,"area":null},{"id":"2209.09174","title":"Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2407.16680","title":"A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2502.07237","title":"DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2502.10177","title":"STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2505.05691","title":"Physics-informed Temporal Difference Metric Learning for Robot Motion Planning","created":"2025-05-09","cited_by_count":6,"area":null},{"id":"2109.15233","title":"Solving the Real Robot Challenge using Deep Reinforcement Learning","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2110.05286","title":"Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning","created":"2021-10-11","cited_by_count":5,"area":null},{"id":"2111.05819","title":"Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention","created":"2021-11-10","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":"2205.09683","title":"Dexterous Robotic Manipulation using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Tasks","created":"2022-05-19","cited_by_count":5,"area":null},{"id":"2208.01960","title":"Learning Object Manipulation Skills from Video via Approximate Differentiable Physics","created":"2022-08-03","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":"2210.01525","title":"Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2210.03729","title":"Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2402.03357","title":"Harnessing Network Effect for Fake News Mitigation: Selecting Debunkers via Self-Imitation Learning","created":"2024-01-28","cited_by_count":5,"area":null},{"id":"2403.08936","title":"Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning","created":"2024-03-13","cited_by_count":5,"area":null},{"id":"2502.08643","title":"A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2103.06370","title":"Causal-aware Safe Policy Improvement for Task-oriented dialogue","created":"2021-03-10","cited_by_count":4,"area":null},{"id":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2203.06250","title":"Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2206.02679","title":"Real2Sim or Sim2Real: Robotics Visual Insertion using Deep Reinforcement Learning and Real2Sim Policy Adaptation","created":"2022-06-06","cited_by_count":4,"area":null},{"id":"2210.09496","title":"CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations","created":"2022-10-18","cited_by_count":4,"area":null},{"id":"2212.01509","title":"Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2408.01334","title":"A Backbone for Long-Horizon Robot Task Understanding","created":"2024-08-02","cited_by_count":4,"area":null},{"id":"2410.09187","title":"Automated Rewards via LLM-Generated Progress Functions","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2101.04736","title":"Bootstrapping Motor Skill Learning with Motion Planning","created":"2021-01-12","cited_by_count":3,"area":null},{"id":"2106.07728","title":"Targeted Data Acquisition for Evolving Negotiation Agents","created":"2021-06-14","cited_by_count":3,"area":null},{"id":"2203.14741","title":"Learning Personalized Human-Aware Robot Navigation Using Virtual Reality Demonstrations from a User Study","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2212.06998","title":"Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning","created":"2022-12-14","cited_by_count":3,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2410.04855","title":"Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2410.15181","title":"GUIDE: Real-Time Human-Shaped Agents","created":"2024-10-19","cited_by_count":3,"area":null},{"id":"2105.11977","title":"Towards Teachable Autotelic Agents","created":"2021-05-25","cited_by_count":2,"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":"2206.05652","title":"Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies","created":"2022-06-12","cited_by_count":2,"area":null},{"id":"2208.03002","title":"A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning","created":"2022-08-05","cited_by_count":2,"area":null},{"id":"2209.09882","title":"Soft Action Priors: Towards Robust Policy Transfer","created":"2022-09-20","cited_by_count":2,"area":null},{"id":"2210.07658","title":"Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2210.12509","title":"Cut-and-Approximate: 3D Shape Reconstruction from Planar Cross-sections with Deep Reinforcement Learning","created":"2022-10-22","cited_by_count":2,"area":null},{"id":"2303.03365","title":"Efficient Skill Acquisition for Complex Manipulation Tasks in Obstructed Environments","created":"2023-03-06","cited_by_count":2,"area":null},{"id":"2303.16469","title":"Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2304.03535","title":"CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning","created":"2023-04-07","cited_by_count":2,"area":null}],"next_cursor":"100"}