{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"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":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"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":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"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":"1605.06432","title":"Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data","created":"2016-05-20","cited_by_count":156},{"id":"1707.06203","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","created":"2017-07-19","cited_by_count":140},{"id":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"2006.04176","title":"Deep active inference agents using Monte-Carlo methods","created":"2020-06-07","cited_by_count":72},{"id":"2007.14535","title":"Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction","created":"2020-07-29","cited_by_count":66},{"id":"1801.10395","title":"Probabilistic Recurrent State-Space Models","created":"2018-01-31","cited_by_count":64},{"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":"1802.03006","title":"Learning and Querying Fast Generative Models for Reinforcement Learning","created":"2018-02-08","cited_by_count":48},{"id":"2002.12636","title":"Reinforcement Learning through Active Inference","created":"2020-02-28","cited_by_count":47},{"id":"2004.08128","title":"Whence the Expected Free Energy?","created":"2020-04-17","cited_by_count":40},{"id":"2009.01791","title":"Action and Perception as Divergence Minimization","created":"2020-09-03","cited_by_count":32},{"id":"1911.10601","title":"Scaling active inference","created":"2019-11-24","cited_by_count":30},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24},{"id":"2110.10083","title":"Contrastive Active Inference","created":"2021-10-19","cited_by_count":21},{"id":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","cited_by_count":21},{"id":"2009.03622","title":"Deep Active Inference for Partially Observable MDPs","created":"2020-09-08","cited_by_count":20},{"id":"2307.00504","title":"On efficient computation in active inference","created":"2023-07-02","cited_by_count":15},{"id":"2311.09589","title":"Mortal Computation: A Foundation for Biomimetic Intelligence","created":"2023-11-16","cited_by_count":15},{"id":"2210.09256","title":"On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning","created":"2022-10-17","cited_by_count":13},{"id":"1904.08149","title":"Bayesian policy selection using active inference","created":"2019-04-17","cited_by_count":12},{"id":"2310.14810","title":"Neural representation in active inference: using generative models to interact with -- and understand -- the lived world","created":"2023-10-23","cited_by_count":4},{"id":"2106.02390","title":"Online reinforcement learning with sparse rewards through an active inference capsule","created":"2021-06-04","cited_by_count":3},{"id":"2109.04155","title":"Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem","created":"2021-09-09","cited_by_count":2},{"id":"2208.05269","title":"A Novel Resource Allocation for Anti-jamming in Cognitive-UAVs: an Active Inference Approach","created":"2022-08-10","cited_by_count":2},{"id":"2211.10419","title":"A Neural Active Inference Model of Perceptual-Motor Learning","created":"2022-11-16","cited_by_count":2}],"next_cursor":null}