{"list":"other","total":60,"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":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"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":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"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":"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":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"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":"1910.07207","title":"Soft Actor-Critic for Discrete Action Settings","created":"2019-10-16","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":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"1911.09291","title":"Scalable methods for computing state similarity in deterministic Markov Decision Processes","created":"2019-11-21","cited_by_count":133},{"id":"1509.01149","title":"Model Predictive Path Integral Control using Covariance Variable Importance Sampling","created":"2015-09-03","cited_by_count":124},{"id":"1704.03012","title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","created":"2017-04-10","cited_by_count":124},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"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":"1604.07255","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","created":"2016-04-25","cited_by_count":90},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"2009.01439","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","created":"2020-09-03","cited_by_count":85},{"id":"1901.10902","title":"InfoBot: Transfer and Exploration via the Information Bottleneck","created":"2019-01-30","cited_by_count":78},{"id":"1612.07307","title":"Loss is its own Reward: Self-Supervision for Reinforcement Learning","created":"2016-12-21","cited_by_count":72},{"id":"1803.06773","title":"Composable Deep Reinforcement Learning for Robotic Manipulation","created":"2018-03-19","cited_by_count":72},{"id":"1909.10618","title":"Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?","created":"2019-09-23","cited_by_count":68},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58},{"id":"1811.07819","title":"Learning Actionable Representations with Goal-Conditioned Policies","created":"2018-11-19","cited_by_count":54},{"id":"1703.08294","title":"Multi-Level Discovery of Deep Options","created":"2017-03-24","cited_by_count":51},{"id":"1807.10366","title":"Robot Motion Planning in Learned Latent Spaces","created":"2018-07-26","cited_by_count":42},{"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":"1710.05373","title":"Robust Locally-Linear Controllable Embedding","created":"2017-10-15","cited_by_count":38},{"id":"1808.00928","title":"Learning Actionable Representations from Visual Observations","created":"2018-08-02","cited_by_count":35},{"id":"1810.11583","title":"Learning Abstract Options","created":"2018-10-27","cited_by_count":31},{"id":"2010.06491","title":"Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning","created":"2020-10-13","cited_by_count":26},{"id":"1712.00004","title":"Learnings Options End-to-End for Continuous Action Tasks","created":"2017-11-30","cited_by_count":24},{"id":"1802.04325","title":"Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation","created":"2018-02-12","cited_by_count":20},{"id":"1812.01488","title":"Natural Option Critic","created":"2018-12-04","cited_by_count":6},{"id":"2010.14289","title":"Affordance as general value function: A computational model","created":"2020-10-27","cited_by_count":5}],"next_cursor":null}