{"list":"other","total":119,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327},{"id":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"2309.13037","title":"GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators","created":"2023-09-22","cited_by_count":189},{"id":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175},{"id":"2111.03043","title":"A System for General In-Hand Object Re-Orientation","created":"2021-11-04","cited_by_count":165},{"id":"1812.06298","title":"Residual Policy Learning","created":"2018-12-15","cited_by_count":164},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2403.07788","title":"DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation","created":"2024-03-12","cited_by_count":160},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"1709.07857","title":"Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping","created":"2017-09-22","cited_by_count":144},{"id":"1903.11239","title":"TossingBot: Learning to Throw Arbitrary Objects with Residual Physics","created":"2019-03-27","cited_by_count":137},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133},{"id":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126},{"id":"2210.04887","title":"In-Hand Object Rotation via Rapid Motor Adaptation","created":"2022-10-10","cited_by_count":118},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111},{"id":"2310.10943","title":"Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning","created":"2023-10-17","cited_by_count":111},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101},{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99},{"id":"2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","created":"2024-01-30","cited_by_count":99},{"id":"2105.08328","title":"Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning","created":"2021-05-18","cited_by_count":92},{"id":"1605.06450","title":"Query-Efficient Imitation Learning for End-to-End Autonomous Driving","created":"2016-05-20","cited_by_count":84},{"id":"2211.09423","title":"DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation","created":"2022-11-17","cited_by_count":84},{"id":"2307.03659","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","created":"2023-07-07","cited_by_count":82},{"id":"2105.03655","title":"FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding","created":"2021-05-08","cited_by_count":81},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79},{"id":"1910.13439","title":"Learning to Manipulate Deformable Objects without Demonstrations","created":"2019-10-29","cited_by_count":77},{"id":"2006.14091","title":"Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences","created":"2020-06-24","cited_by_count":71},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"1906.08880","title":"Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks","created":"2019-06-20","cited_by_count":67},{"id":"1802.01744","title":"Shared Autonomy via Deep Reinforcement Learning","created":"2018-02-06","cited_by_count":66},{"id":"2301.02555","title":"\"No, to the Right\" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy","created":"2023-01-06","cited_by_count":60},{"id":"2210.12209","title":"Motion Policy Networks","created":"2022-10-21","cited_by_count":55},{"id":"2211.00600","title":"Interactive Imitation Learning in Robotics: A Survey","created":"2022-10-31","cited_by_count":55},{"id":"2205.03532","title":"Factory: Fast Contact for Robotic Assembly","created":"2022-05-07","cited_by_count":54},{"id":"2211.09006","title":"ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point Clouds","created":"2022-11-16","cited_by_count":54},{"id":"2305.17110","title":"IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality","created":"2023-05-26","cited_by_count":53},{"id":"2309.00987","title":"Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation","created":"2023-09-02","cited_by_count":49},{"id":"1503.07619","title":"Shared Autonomy via Hindsight Optimization","created":"2015-03-26","cited_by_count":46},{"id":"2209.02778","title":"Multi-skill Mobile Manipulation for Object Rearrangement","created":"2022-09-06","cited_by_count":46},{"id":"1803.05580","title":"Feedback Control For Cassie With Deep Reinforcement Learning","created":"2018-03-15","cited_by_count":45},{"id":"2203.17275","title":"DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools","created":"2022-03-31","cited_by_count":44},{"id":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44},{"id":"1909.09906","title":"Leveraging Human Guidance for Deep Reinforcement Learning Tasks","created":"2019-09-21","cited_by_count":42},{"id":"2105.12949","title":"A Survey on Interactive Reinforcement Learning: Design Principles and Open Challenges","created":"2021-05-27","cited_by_count":41},{"id":"1903.01066","title":"Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly","created":"2019-03-04","cited_by_count":39},{"id":"2208.01160","title":"Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot","created":"2022-08-01","cited_by_count":38},{"id":"2310.17552","title":"Model-Based Runtime Monitoring with Interactive Imitation Learning","created":"2023-10-26","cited_by_count":38},{"id":"2404.03729","title":"JUICER: Data-Efficient Imitation Learning for Robotic Assembly","created":"2024-04-04","cited_by_count":38},{"id":"2108.05382","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","created":"2021-08-11","cited_by_count":35},{"id":"2004.14404","title":"Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks","created":"2020-04-29","cited_by_count":34},{"id":"2005.03210","title":"Shared Autonomy with Learned Latent Actions","created":"2020-05-07","cited_by_count":34},{"id":"1306.6294","title":"Learning Trajectory Preferences for Manipulators via Iterative Improvement","created":"2013-06-26","cited_by_count":31}],"next_cursor":"100"}