{"list":"other","total":56,"rows":[{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"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":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1911.08453","title":"Planning with Goal-Conditioned Policies","created":"2019-11-19","cited_by_count":149},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1906.05030","title":"Fast Task Inference with Variational Intrinsic Successor Features","created":"2019-06-12","cited_by_count":133},{"id":"1704.03012","title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","created":"2017-04-10","cited_by_count":124},{"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":"1703.00956","title":"A Laplacian Framework for Option Discovery in Reinforcement Learning","created":"2017-03-02","cited_by_count":110},{"id":"1810.01257","title":"Near-Optimal Representation Learning for Hierarchical Reinforcement Learning","created":"2018-10-02","cited_by_count":110},{"id":"1810.02274","title":"Episodic Curiosity through Reachability","created":"2018-10-04","cited_by_count":109},{"id":"1812.07626","title":"Universal Successor Features Approximators","created":"2018-12-18","cited_by_count":103},{"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":"2006.09641","title":"Automatic Curriculum Learning through Value Disagreement","created":"2020-06-17","cited_by_count":87},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"1908.06976","title":"A survey on intrinsic motivation in reinforcement learning","created":"2019-08-19","cited_by_count":81},{"id":"2011.12491","title":"World Model as a Graph: Learning Latent Landmarks for Planning","created":"2020-11-25","cited_by_count":69},{"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":"1811.07819","title":"Learning Actionable Representations with Goal-Conditioned Policies","created":"2018-11-19","cited_by_count":54},{"id":"1908.05451","title":"Mapping State Space using Landmarks for Universal Goal Reaching","created":"2019-08-15","cited_by_count":44},{"id":"1905.08786","title":"Maximum Entropy-Regularized Multi-Goal Reinforcement Learning","created":"2019-05-21","cited_by_count":40},{"id":"2101.02055","title":"Geometric Entropic Exploration","created":"2021-01-06","cited_by_count":32},{"id":"1810.11583","title":"Learning Abstract Options","created":"2018-10-27","cited_by_count":31},{"id":"2003.06417","title":"Sparse Graphical Memory for Robust Planning","created":"2020-03-13","cited_by_count":31},{"id":"1805.08180","title":"Hierarchical Reinforcement Learning with Hindsight","created":"2018-05-21","cited_by_count":26},{"id":"2105.14750","title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","created":"2021-05-31","cited_by_count":17},{"id":"1807.01521","title":"Curiosity Driven Exploration of Learned Disentangled Goal Spaces","created":"2018-07-04","cited_by_count":16},{"id":"2010.02302","title":"Latent World Models For Intrinsically Motivated Exploration","created":"2020-10-05","cited_by_count":15},{"id":"1703.07718","title":"Independently Controllable Features","created":"2017-03-22","cited_by_count":11},{"id":"1901.09720","title":"CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments","created":"2019-01-28","cited_by_count":10},{"id":"2008.04388","title":"GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning","created":"2020-08-10","cited_by_count":9},{"id":"1912.13414","title":"Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards","created":"2019-12-21","cited_by_count":4},{"id":"2003.05878","title":"Option Discovery in the Absence of Rewards with Manifold Analysis","created":"2020-03-12","cited_by_count":3},{"id":"2006.12903","title":"ELSIM: End-to-end learning of reusable skills through intrinsic motivation","created":"2020-06-23","cited_by_count":3}],"next_cursor":null}