{"list":"other","total":89,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"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":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"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":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1604.00772","title":"The CMA Evolution Strategy: A Tutorial","created":"2016-04-04","cited_by_count":377},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"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":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"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":"2002.01650","title":"Concept Whitening for Interpretable Image Recognition","created":"2020-02-05","cited_by_count":225},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"1802.08760","title":"Sensitivity and Generalization in Neural Networks: an Empirical Study","created":"2018-02-23","cited_by_count":189},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"1909.13789","title":"Hamiltonian Generative Networks","created":"2019-09-30","cited_by_count":137},{"id":"1903.12436","title":"From Variational to Deterministic Autoencoders","created":"2019-03-29","cited_by_count":133},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"1609.02200","title":"Discrete Variational Autoencoders","created":"2016-09-07","cited_by_count":125},{"id":"1806.02426","title":"Deep Variational Reinforcement Learning for POMDPs","created":"2018-06-06","cited_by_count":125},{"id":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"1811.11359","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","created":"2018-11-28","cited_by_count":102},{"id":"2001.07203","title":"Active inference on discrete state-spaces: a synthesis","created":"2020-01-20","cited_by_count":92},{"id":"1901.03416","title":"Preventing Posterior Collapse with delta-VAEs","created":"2019-01-10","cited_by_count":86},{"id":"1703.01732","title":"Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning","created":"2017-03-06","cited_by_count":83},{"id":"2011.04217","title":"NeuralSim: Augmenting Differentiable Simulators with Neural Networks","created":"2020-11-09","cited_by_count":82},{"id":"1712.00378","title":"Time Limits in Reinforcement Learning","created":"2017-12-01","cited_by_count":79},{"id":"1512.04455","title":"Memory-based control with recurrent neural networks","created":"2015-12-14","cited_by_count":78},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75},{"id":"2006.04176","title":"Deep active inference agents using Monte-Carlo methods","created":"2020-06-07","cited_by_count":72},{"id":"1705.09156","title":"The free energy principle for action and perception: A mathematical review","created":"2017-05-24","cited_by_count":66},{"id":"2005.08068","title":"Model-Augmented Actor-Critic: Backpropagating through Paths","created":"2020-05-16","cited_by_count":63},{"id":"2006.04120","title":"Sophisticated Inference","created":"2020-06-07","cited_by_count":56},{"id":"1907.03876","title":"Deep Active Inference as Variational Policy Gradients","created":"2019-07-08","cited_by_count":53},{"id":"2101.08286","title":"Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem","created":"2021-01-20","cited_by_count":53},{"id":"2112.01871","title":"Active Inference in Robotics and Artificial Agents: Survey and Challenges","created":"2021-12-03","cited_by_count":52},{"id":"1802.03006","title":"Learning and Querying Fast Generative Models for Reinforcement Learning","created":"2018-02-08","cited_by_count":48},{"id":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48},{"id":"2002.12636","title":"Reinforcement Learning through Active Inference","created":"2020-02-28","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":"2102.09532","title":"Clockwork Variational Autoencoders","created":"2021-02-18","cited_by_count":42},{"id":"2004.08128","title":"Whence the Expected Free Energy?","created":"2020-04-17","cited_by_count":40},{"id":"1607.03474","title":"Recurrent Highway Networks","created":"2016-07-12","cited_by_count":37},{"id":"1911.10601","title":"Scaling active inference","created":"2019-11-24","cited_by_count":30},{"id":"2001.05847","title":"End-to-End Pixel-Based Deep Active Inference for Body Perception and Action","created":"2019-12-28","cited_by_count":24},{"id":"2110.10083","title":"Contrastive Active Inference","created":"2021-10-19","cited_by_count":21},{"id":"2001.11841","title":"Learning Perception and Planning with Deep Active Inference","created":"2020-01-30","cited_by_count":19},{"id":"2008.02430","title":"Contrastive Variational Reinforcement Learning for Complex Observations","created":"2020-08-06","cited_by_count":15},{"id":"1904.08149","title":"Bayesian policy selection using active inference","created":"2019-04-17","cited_by_count":12},{"id":"2106.04316","title":"Exploration and preference satisfaction trade-off in reward-free learning","created":"2021-06-08","cited_by_count":12},{"id":"2110.11236","title":"Variational Predictive Routing with Nested Subjective Timescales","created":"2021-10-21","cited_by_count":9},{"id":"2002.12253","title":"MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference","created":"2020-02-27","cited_by_count":7},{"id":"2002.04501","title":"Some interesting observations on the free energy principle","created":"2020-02-05","cited_by_count":4}],"next_cursor":null}