{"list":"other","total":53,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"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":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"2006.07114","title":"Knowledge Distillation Meets Self-Supervision","created":"2020-06-12","cited_by_count":142},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"1807.10299","title":"Variational Option Discovery Algorithms","created":"2018-07-26","cited_by_count":122},{"id":"2002.03647","title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","created":"2020-02-10","cited_by_count":122},{"id":"1811.01848","title":"Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control","created":"2018-11-05","cited_by_count":113},{"id":"1811.11359","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","created":"2018-11-28","cited_by_count":102},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"1802.09081","title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","created":"2018-02-25","cited_by_count":89},{"id":"1908.06976","title":"A survey on intrinsic motivation in reinforcement learning","created":"2019-08-19","cited_by_count":81},{"id":"1310.1863","title":"Empowerment -- an Introduction","created":"2013-10-07","cited_by_count":68},{"id":"1907.08225","title":"Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery","created":"2019-07-18","cited_by_count":68},{"id":"2002.09253","title":"Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration","created":"2020-02-21","cited_by_count":68},{"id":"1704.03073","title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","created":"2017-04-10","cited_by_count":63},{"id":"1301.4862","title":"Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots","created":"2013-01-21","cited_by_count":58},{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58},{"id":"1806.02813","title":"Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings","created":"2018-06-07","cited_by_count":52},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"1910.11670","title":"Contextual Imagined Goals for Self-Supervised Robotic Learning","created":"2019-10-23","cited_by_count":40},{"id":"1806.04640","title":"Unsupervised Meta-Learning for Reinforcement Learning","created":"2018-06-12","cited_by_count":39},{"id":"1810.01531","title":"A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning","created":"2018-10-02","cited_by_count":36},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36},{"id":"1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","created":"2019-12-09","cited_by_count":34},{"id":"2009.01791","title":"Action and Perception as Divergence Minimization","created":"2020-09-03","cited_by_count":32},{"id":"2008.00614","title":"Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning","created":"2020-08-03","cited_by_count":26},{"id":"1811.09083","title":"Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning","created":"2018-11-22","cited_by_count":24},{"id":"1803.00781","title":"Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration","created":"2018-03-02","cited_by_count":23},{"id":"1901.00943","title":"Self-supervised Learning of Image Embedding for Continuous Control","created":"2019-01-03","cited_by_count":16},{"id":"2011.07589","title":"DIRL: Domain-Invariant Representation Learning for Sim-to-Real Transfer","created":"2020-11-15","cited_by_count":13},{"id":"2008.04388","title":"GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning","created":"2020-08-10","cited_by_count":9}],"next_cursor":null}