{"list":"other","total":155,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"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":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"id":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"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":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"id":"1909.11652","title":"Deep Dynamics Models for Learning Dexterous Manipulation","created":"2019-09-25","cited_by_count":206},{"id":"2101.06286","title":"Reinforcement learning based recommender systems: A survey","created":"2021-01-15","cited_by_count":188},{"id":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187},{"id":"2406.10454","title":"HumanPlus: Humanoid Shadowing and Imitation from Humans","created":"2024-06-15","cited_by_count":185},{"id":"1812.07252","title":"Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks","created":"2018-12-18","cited_by_count":174},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2306.14874","title":"ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots","created":"2023-06-26","cited_by_count":152},{"id":"2211.07638","title":"Legged Locomotion in Challenging Terrains using Egocentric Vision","created":"2022-11-14","cited_by_count":151},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149},{"id":"1907.03146","title":"A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms","created":"2019-07-06","cited_by_count":142},{"id":"2212.03238","title":"Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior","created":"2022-12-06","cited_by_count":138},{"id":"1703.08862","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","created":"2017-03-26","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":"1806.07851","title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","created":"2018-06-20","cited_by_count":131},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131},{"id":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"2110.05113","title":"Learning High-Speed Flight in the Wild","created":"2021-10-11","cited_by_count":128},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"id":"2210.10044","title":"Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion","created":"2022-10-18","cited_by_count":121},{"id":"1609.07845","title":"Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning","created":"2016-09-26","cited_by_count":118},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"2004.12570","title":"The Ingredients of Real-World Robotic Reinforcement Learning","created":"2020-04-27","cited_by_count":117},{"id":"2103.14295","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","created":"2021-03-26","cited_by_count":116},{"id":"1805.01956","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","created":"2018-05-04","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":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106},{"id":"1804.06557","title":"The Limits and Potentials of Deep Learning for Robotics","created":"2018-04-18","cited_by_count":104},{"id":"2002.05700","title":"BADGR: An Autonomous Self-Supervised Learning-Based Navigation System","created":"2020-02-13","cited_by_count":102},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101},{"id":"1703.00420","title":"Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation","created":"2017-03-01","cited_by_count":98},{"id":"2011.01387","title":"Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition","created":"2020-11-02","cited_by_count":96},{"id":"1707.05110","title":"Control of a Quadrotor with Reinforcement Learning","created":"2017-07-17","cited_by_count":92},{"id":"2105.08328","title":"Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning","created":"2021-05-18","cited_by_count":92},{"id":"1809.03531","title":"PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning","created":"2018-09-10","cited_by_count":90},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83},{"id":"2106.14440","title":"VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects","created":"2021-06-28","cited_by_count":80},{"id":"2401.08553","title":"FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning","created":"2024-01-16","cited_by_count":80},{"id":"2107.03996","title":"Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers","created":"2021-07-08","cited_by_count":79},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78},{"id":"1709.10489","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","created":"2017-09-29","cited_by_count":77},{"id":"1910.13439","title":"Learning to Manipulate Deformable Objects without Demonstrations","created":"2019-10-29","cited_by_count":77},{"id":"2111.01674","title":"Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots","created":"2021-10-25","cited_by_count":76},{"id":"2401.17583","title":"Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion","created":"2024-01-31","cited_by_count":73},{"id":"2110.05457","title":"Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World","created":"2021-10-11","cited_by_count":71},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71},{"id":"1809.10124","title":"Learning Navigation Behaviors End-to-End with AutoRL","created":"2018-09-26","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":"2012.05810","title":"Multi-expert learning of adaptive legged locomotion","created":"2020-12-10","cited_by_count":67},{"id":"1802.01744","title":"Shared Autonomy via Deep Reinforcement Learning","created":"2018-02-06","cited_by_count":66},{"id":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62},{"id":"2011.02404","title":"Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion","created":"2020-11-04","cited_by_count":59},{"id":"2205.15299","title":"Adapting Rapid Motor Adaptation for Bipedal Robots","created":"2022-05-30","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":"2208.10552","title":"SpeedFolding: Learning Efficient Bimanual Folding of Garments","created":"2022-08-22","cited_by_count":52},{"id":"2209.12827","title":"Advanced Skills by Learning Locomotion and Local Navigation End-to-End","created":"2022-09-26","cited_by_count":52},{"id":"1910.11689","title":"Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning","created":"2019-10-24","cited_by_count":49},{"id":"2209.05309","title":"GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots","created":"2022-09-12","cited_by_count":48},{"id":"2405.01792","title":"Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots","created":"2024-05-03","cited_by_count":48},{"id":"2202.10796","title":"A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight","created":"2022-02-22","cited_by_count":47},{"id":"1903.04628","title":"Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors","created":"2019-03-11","cited_by_count":45},{"id":"1909.13874","title":"Efficient Bimanual Manipulation Using Learned Task Schemas","created":"2019-09-30","cited_by_count":45},{"id":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44},{"id":"1908.05224","title":"Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real","created":"2019-08-13","cited_by_count":42},{"id":"2203.04923","title":"On-Robot Learning With Equivariant Models","created":"2022-03-09","cited_by_count":42},{"id":"2304.00410","title":"ASC: Adaptive Skill Coordination for Robotic Mobile Manipulation","created":"2023-04-01","cited_by_count":42}],"next_cursor":"100"}