{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"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":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1901.09948","title":"Surrogate Gradient Learning in Spiking Neural Networks","created":"2019-01-28","cited_by_count":626},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"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":"1602.05179","title":"Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation","created":"2016-02-16","cited_by_count":259},{"id":"1609.01596","title":"Direct Feedback Alignment Provides Learning in Deep Neural Networks","created":"2016-09-06","cited_by_count":240},{"id":"1701.02434","title":"A Conceptual Introduction to Hamiltonian Monte Carlo","created":"2017-01-10","cited_by_count":209},{"id":"1909.11652","title":"Deep Dynamics Models for Learning Dexterous Manipulation","created":"2019-09-25","cited_by_count":206},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"1906.05274","title":"Efficient Exploration via State Marginal Matching","created":"2019-06-12","cited_by_count":188},{"id":"1403.5341","title":"An Information-Theoretic Analysis of Thompson Sampling","created":"2014-03-21","cited_by_count":178},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"id":"1506.04696","title":"A Complete Recipe for Stochastic Gradient MCMC","created":"2015-06-15","cited_by_count":146},{"id":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"2001.07203","title":"Active inference on discrete state-spaces: a synthesis","created":"2020-01-20","cited_by_count":92},{"id":"1802.02550","title":"Semi-Amortized Variational Autoencoders","created":"2018-02-07","cited_by_count":83},{"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":"1510.05067","title":"How Important is Weight Symmetry in Backpropagation?","created":"2015-10-17","cited_by_count":58},{"id":"1812.03973","title":"Bayesian Layers: A Module for Neural Network Uncertainty","created":"2018-12-10","cited_by_count":57},{"id":"2006.14331","title":"A Theoretical Framework for Target Propagation","created":"2020-06-25","cited_by_count":57},{"id":"1907.03876","title":"Deep Active Inference as Variational Policy Gradients","created":"2019-07-08","cited_by_count":53},{"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":"1906.10184","title":"A free energy principle for a particular physics","created":"2019-06-24","cited_by_count":40},{"id":"1907.04202","title":"Variational Inference MPC for Bayesian Model-based Reinforcement Learning","created":"2019-07-08","cited_by_count":39},{"id":"2009.01791","title":"Action and Perception as Divergence Minimization","created":"2020-09-03","cited_by_count":32},{"id":"1906.04554","title":"Principled Training of Neural Networks with Direct Feedback Alignment","created":"2019-06-11","cited_by_count":23},{"id":"1810.11530","title":"Automatic differentiation in ML: Where we are and where we should be going","created":"2018-10-26","cited_by_count":20},{"id":"1812.07965","title":"Deep learning with asymmetric connections and Hebbian updates","created":"2018-11-19","cited_by_count":16},{"id":"2007.15139","title":"Deriving Differential Target Propagation from Iterating Approximate Inverses","created":"2020-07-29","cited_by_count":15},{"id":"1510.02777","title":"Early Inference in Energy-Based Models Approximates Back-Propagation","created":"2015-10-09","cited_by_count":13},{"id":"1711.11542","title":"Learning to Adapt by Minimizing Discrepancy","created":"2017-11-30","cited_by_count":12},{"id":"1904.08149","title":"Bayesian policy selection using active inference","created":"2019-04-17","cited_by_count":12},{"id":"2010.01047","title":"Relaxing the Constraints on Predictive Coding Models","created":"2020-10-02","cited_by_count":12},{"id":"1506.06472","title":"A Theory of Local Learning, the Learning Channel, and the Optimality of Backpropagation","created":"2015-06-22","cited_by_count":11},{"id":"2009.05359","title":"Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain","created":"2020-09-11","cited_by_count":11},{"id":"1901.00696","title":"The Extended Kalman Filter is a Natural Gradient Descent in Trajectory Space","created":"2019-01-03","cited_by_count":10},{"id":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","cited_by_count":10},{"id":"2007.05838","title":"Control as Hybrid Inference","created":"2020-07-11","cited_by_count":9},{"id":"1805.07206","title":"Approximate Bayesian inference in spatial environments","created":"2018-05-18","cited_by_count":8},{"id":"1707.01806","title":"An active inference implementation of phototaxis","created":"2017-07-06","cited_by_count":6},{"id":"1304.1920","title":"Generalizing the No-U-Turn Sampler to Riemannian Manifolds","created":"2013-04-06","cited_by_count":5},{"id":"2002.04501","title":"Some interesting observations on the free energy principle","created":"2020-02-05","cited_by_count":4},{"id":"2007.09704","title":"Parcels and particles: Markov blankets in the brain","created":"2020-07-19","cited_by_count":4},{"id":"1806.02649","title":"The modularity of action and perception revisited using control theory and active inference","created":"2018-06-07","cited_by_count":3},{"id":"1903.09247","title":"The Hitchhiker's Guide to Nonlinear Filtering","created":"2019-03-21","cited_by_count":2},{"id":"1910.12151","title":"Making Predictive Coding Networks Generative","created":"2019-10-26","cited_by_count":2},{"id":"2006.11495","title":"Predictions in the eye of the beholder: an active inference account of Watt governors","created":"2020-06-20","cited_by_count":2},{"id":"2003.06751","title":"Robot Playing Kendama with Model-Based and Model-Free Reinforcement Learning","created":"2020-03-15","cited_by_count":1}],"next_cursor":null}