{"list":"other","total":55,"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"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":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"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":"1906.02736","title":"DeepMDP: Learning Continuous Latent Space Models for Representation Learning","created":"2019-06-06","cited_by_count":207},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"id":"1609.01704","title":"Hierarchical Multiscale Recurrent Neural Networks","created":"2016-09-06","cited_by_count":104},{"id":"1904.12165","title":"Improved Conditional VRNNs for Video Prediction","created":"2019-04-27","cited_by_count":104},{"id":"2101.02722","title":"The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels","created":"2021-01-07","cited_by_count":100},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"2002.05379","title":"The Conditional Entropy Bottleneck","created":"2020-02-13","cited_by_count":75},{"id":"1903.01434","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","created":"2019-03-04","cited_by_count":74},{"id":"1402.3511","title":"A Clockwork RNN","created":"2014-02-14","cited_by_count":72},{"id":"1706.07845","title":"HARP: Hierarchical Representation Learning for Networks","created":"2017-06-23","cited_by_count":58},{"id":"2007.12401","title":"Predictive Information Accelerates Learning in RL","created":"2020-07-24","cited_by_count":56},{"id":"1909.04607","title":"Discovery of Useful Questions as Auxiliary Tasks","created":"2019-09-10","cited_by_count":45},{"id":"1911.09737","title":"Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks","created":"2019-11-21","cited_by_count":45},{"id":"2111.05424","title":"AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale","created":"2021-11-09","cited_by_count":44},{"id":"2102.09532","title":"Clockwork Variational Autoencoders","created":"2021-02-18","cited_by_count":42},{"id":"1910.00775","title":"Variational Temporal Abstraction","created":"2019-10-02","cited_by_count":38},{"id":"1905.07195","title":"CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network","created":"2019-05-17","cited_by_count":25},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25},{"id":"1807.06763","title":"General Value Function Networks","created":"2018-07-18","cited_by_count":16},{"id":"1709.08520","title":"Predictive-State Decoders: Encoding the Future into Recurrent Networks","created":"2017-09-25","cited_by_count":11},{"id":"2110.04935","title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning","created":"2021-10-11","cited_by_count":10},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3}],"next_cursor":null}