{"list":"other","total":55,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1707.00183","title":"Teacher-Student Curriculum Learning","created":"2017-07-01","cited_by_count":210},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"1702.00539","title":"Procedural Content Generation via Machine Learning (PCGML)","created":"2017-02-02","cited_by_count":137},{"id":"1903.11239","title":"TossingBot: Learning to Throw Arbitrary Objects with Residual Physics","created":"2019-03-27","cited_by_count":137},{"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":"1704.03012","title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","created":"2017-04-10","cited_by_count":124},{"id":"2002.03647","title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","created":"2020-02-10","cited_by_count":122},{"id":"1910.07224","title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments","created":"2019-10-16","cited_by_count":119},{"id":"1309.2660","title":"Data-Driven Grasp Synthesis - A Survey","created":"2013-09-10","cited_by_count":106},{"id":"2003.08536","title":"Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions","created":"2020-03-19","cited_by_count":106},{"id":"1811.11359","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","created":"2018-11-28","cited_by_count":102},{"id":"1710.09767","title":"Meta Learning Shared Hierarchies","created":"2017-10-26","cited_by_count":93},{"id":"2001.09212","title":"PCGRL: Procedural Content Generation via Reinforcement Learning","created":"2020-01-24","cited_by_count":90},{"id":"1708.02190","title":"Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning","created":"2017-08-07","cited_by_count":83},{"id":"2012.07277","title":"Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs","created":"2020-12-14","cited_by_count":83},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"1704.03073","title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","created":"2017-04-10","cited_by_count":63},{"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":"1806.09266","title":"Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision","created":"2018-06-25","cited_by_count":52},{"id":"1910.13675","title":"Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly","created":"2019-10-30","cited_by_count":51},{"id":"1907.04053","title":"Procedural Content Generation through Quality Diversity","created":"2019-07-09","cited_by_count":45},{"id":"1806.04640","title":"Unsupervised Meta-Learning for Reinforcement Learning","created":"2018-06-12","cited_by_count":39},{"id":"1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","created":"2019-12-09","cited_by_count":34},{"id":"1903.01588","title":"Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter","created":"2019-03-04","cited_by_count":30},{"id":"1805.10309","title":"Learning Self-Imitating Diverse Policies","created":"2018-05-25","cited_by_count":29},{"id":"1909.04121","title":"AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers","created":"2019-09-09","cited_by_count":28},{"id":"1910.13395","title":"Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation","created":"2019-10-29","cited_by_count":24},{"id":"2007.00350","title":"Adaptive Procedural Task Generation for Hard-Exploration Problems","created":"2020-07-01","cited_by_count":20},{"id":"1802.09484","title":"Disentangling the independently controllable factors of variation by interacting with the world","created":"2018-02-26","cited_by_count":16},{"id":"1806.03793","title":"Context-Aware Policy Reuse","created":"2018-06-11","cited_by_count":16},{"id":"2008.06073","title":"Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter","created":"2020-08-13","cited_by_count":16},{"id":"1706.06383","title":"Programmable Agents","created":"2017-06-20","cited_by_count":14},{"id":"1709.08201","title":"An Optimal Online Method of Selecting Source Policies for Reinforcement Learning","created":"2017-09-24","cited_by_count":13}],"next_cursor":null}