{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"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":"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","created":"2015-06-07","cited_by_count":362},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"2011.10650","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","created":"2020-11-20","cited_by_count":264},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"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":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"1806.02426","title":"Deep Variational Reinforcement Learning for POMDPs","created":"2018-06-06","cited_by_count":125},{"id":"1807.10299","title":"Variational Option Discovery Algorithms","created":"2018-07-26","cited_by_count":122},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122},{"id":"1606.03813","title":"Towards an integration of deep learning and neuroscience","created":"2016-06-13","cited_by_count":78},{"id":"2006.04176","title":"Deep active inference agents using Monte-Carlo methods","created":"2020-06-07","cited_by_count":72},{"id":"1907.03876","title":"Deep Active Inference as Variational Policy Gradients","created":"2019-07-08","cited_by_count":53},{"id":"1912.10703","title":"Variational Recurrent Models for Solving Partially Observable Control Tasks","created":"2019-12-23","cited_by_count":47},{"id":"1709.02341","title":"Deep Active Inference","created":"2017-09-07","cited_by_count":44},{"id":"2006.12964","title":"On the Relationship Between Active Inference and Control as Inference","created":"2020-06-23","cited_by_count":42},{"id":"2007.03750","title":"Deep Reinforcement Learning and its Neuroscientific Implications","created":"2020-07-07","cited_by_count":33},{"id":"2009.01791","title":"Action and Perception as Divergence Minimization","created":"2020-09-03","cited_by_count":32},{"id":"2011.05286","title":"Continual Learning of Control Primitives: Skill Discovery via Reset-Games","created":"2020-11-10","cited_by_count":29},{"id":"1703.03078","title":"Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning","created":"2017-03-08","cited_by_count":27},{"id":"2110.10083","title":"Contrastive Active Inference","created":"2021-10-19","cited_by_count":21},{"id":"2208.08731","title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","created":"2022-08-18","cited_by_count":21},{"id":"1903.01599","title":"Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future","created":"2019-03-05","cited_by_count":17},{"id":"1802.08864","title":"One Big Net For Everything","created":"2018-02-24","cited_by_count":16},{"id":"1908.06663","title":"Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems","created":"2019-08-19","cited_by_count":13},{"id":"2005.14656","title":"Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network","created":"2020-05-27","cited_by_count":5},{"id":"2202.09976","title":"Goal-directed Planning and Goal Understanding by Active Inference: Evaluation Through Simulated and Physical Robot Experiments","created":"2022-02-21","cited_by_count":4},{"id":"1706.02444","title":"Predictive Coding-based Deep Dynamic Neural Network for Visuomotor Learning","created":"2017-06-08","cited_by_count":3}],"next_cursor":null}