{"list":"other","total":66,"rows":[{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","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":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"1402.0590","title":"A Survey of Multi-Objective Sequential Decision-Making","created":"2014-02-04","cited_by_count":242},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"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":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"1804.02717","title":"DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills","created":"2018-04-08","cited_by_count":163},{"id":"1812.11103","title":"Learning to Walk via Deep Reinforcement Learning","created":"2018-12-26","cited_by_count":158},{"id":"2211.07638","title":"Legged Locomotion in Challenging Terrains using Egocentric Vision","created":"2022-11-14","cited_by_count":151},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","cited_by_count":150},{"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":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"1710.03748","title":"Emergent Complexity via Multi-Agent Competition","created":"2017-10-10","cited_by_count":120},{"id":"2002.08550","title":"Learning to Walk in the Real World with Minimal Human Effort","created":"2020-02-20","cited_by_count":111},{"id":"1710.03641","title":"Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments","created":"2017-10-10","cited_by_count":108},{"id":"1905.09808","title":"MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies","created":"2019-05-23","cited_by_count":108},{"id":"1901.08106","title":"Open-ended Learning in Symmetric Zero-sum Games","created":"2019-01-23","cited_by_count":96},{"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":"2105.08328","title":"Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning","created":"2021-05-18","cited_by_count":92},{"id":"2202.05481","title":"Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion","created":"2022-02-11","cited_by_count":88},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87},{"id":"2208.07860","title":"A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning","created":"2022-08-16","cited_by_count":83},{"id":"1803.03835","title":"Kickstarting Deep Reinforcement Learning","created":"2018-03-10","cited_by_count":81},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63},{"id":"1902.07151","title":"Emergent Coordination Through Competition","created":"2019-02-19","cited_by_count":57},{"id":"1903.01390","title":"Sim-to-Real Transfer for Biped Locomotion","created":"2019-03-04","cited_by_count":56},{"id":"1905.01240","title":"Information asymmetry in KL-regularized RL","created":"2019-05-03","cited_by_count":53},{"id":"2005.07513","title":"A Distributional View on Multi-Objective Policy Optimization","created":"2020-05-15","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":"2210.04932","title":"NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields","created":"2022-10-10","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":"2010.14274","title":"Behavior Priors for Efficient Reinforcement Learning","created":"2020-10-27","cited_by_count":41},{"id":"2304.01159","title":"DribbleBot: Dynamic Legged Manipulation in the Wild","created":"2023-04-03","cited_by_count":40},{"id":"2303.11330","title":"Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion","created":"2023-03-20","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":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33},{"id":"1901.07517","title":"Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning","created":"2019-01-22","cited_by_count":32},{"id":"2007.15588","title":"Data-efficient Hindsight Off-policy Option Learning","created":"2020-07-30","cited_by_count":31},{"id":"2203.17138","title":"Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors","created":"2022-03-31","cited_by_count":30},{"id":"2210.04435","title":"Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning","created":"2022-10-10","cited_by_count":23},{"id":"2303.05486","title":"Learning Arm-Assisted Fall Damage Reduction and Recovery for Legged Mobile Manipulators","created":"2023-03-09","cited_by_count":22},{"id":"2303.17479","title":"Event-based Agile Object Catching with a Quadrupedal Robot","created":"2023-03-30","cited_by_count":22},{"id":"2303.03724","title":"Learning Bipedal Walking for Humanoids with Current Feedback","created":"2023-03-07","cited_by_count":18},{"id":"1903.09537","title":"Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie","created":"2019-03-22","cited_by_count":14},{"id":"2008.12228","title":"Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion","created":"2020-08-06","cited_by_count":10},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10},{"id":"2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","created":"2022-11-24","cited_by_count":6}],"next_cursor":null}