{"list":"other","total":56,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"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":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"1709.10089","title":"Overcoming Exploration in Reinforcement Learning with Demonstrations","created":"2017-09-28","cited_by_count":340},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166},{"id":"1802.08705","title":"PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning","created":"2018-02-23","cited_by_count":150},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112},{"id":"2006.12122","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","created":"2020-06-22","cited_by_count":88},{"id":"1708.02190","title":"Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning","created":"2017-08-07","cited_by_count":83},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"id":"2109.13841","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","created":"2021-09-28","cited_by_count":83},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"2110.15360","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","created":"2021-10-28","cited_by_count":65},{"id":"1807.03480","title":"Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration","created":"2018-07-10","cited_by_count":61},{"id":"2103.00589","title":"Learning Symbolic Operators for Task and Motion Planning","created":"2021-02-28","cited_by_count":58},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58},{"id":"1804.07779","title":"PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making","created":"2018-04-20","cited_by_count":52},{"id":"2203.09634","title":"Predicate Invention for Bilevel Planning","created":"2022-03-17","cited_by_count":49},{"id":"2006.05398","title":"Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image","created":"2020-06-09","cited_by_count":48},{"id":"1909.13874","title":"Efficient Bimanual Manipulation Using Learned Task Schemas","created":"2019-09-30","cited_by_count":45},{"id":"1904.12691","title":"DAC: The Double Actor-Critic Architecture for Learning Options","created":"2019-04-29","cited_by_count":43},{"id":"2105.14074","title":"Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning","created":"2021-05-28","cited_by_count":43},{"id":"2011.08424","title":"Deep Affordance Foresight: Planning Through What Can Be Done in the Future","created":"2020-11-17","cited_by_count":41},{"id":"2012.03548","title":"Reset-Free Lifelong Learning with Skill-Space Planning","created":"2020-12-07","cited_by_count":38},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37},{"id":"2107.12931","title":"Autonomous Reinforcement Learning via Subgoal Curricula","created":"2021-07-27","cited_by_count":33},{"id":"1909.13072","title":"Regression Planning Networks","created":"2019-09-28","cited_by_count":32},{"id":"2003.06417","title":"Sparse Graphical Memory for Robust Planning","created":"2020-03-13","cited_by_count":31},{"id":"1803.00967","title":"Active model learning and diverse action sampling for task and motion planning","created":"2018-03-02","cited_by_count":28},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27},{"id":"2203.00397","title":"A Theory of Abstraction in Reinforcement Learning","created":"2022-03-01","cited_by_count":27},{"id":"2012.13037","title":"SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning","created":"2020-12-24","cited_by_count":23},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22},{"id":"2007.00350","title":"Adaptive Procedural Task Generation for Hard-Exploration Problems","created":"2020-07-01","cited_by_count":20},{"id":"2109.08771","title":"Search-Based Task Planning with Learned Skill Effect Models for Lifelong Robotic Manipulation","created":"2021-09-17","cited_by_count":20},{"id":"2205.07993","title":"Generalizable Task Planning through Representation Pretraining","created":"2022-05-16","cited_by_count":19},{"id":"2007.13202","title":"CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs","created":"2020-07-26","cited_by_count":18},{"id":"1810.11177","title":"Learning sparse relational transition models","created":"2018-10-26","cited_by_count":11}],"next_cursor":null}