{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T10:41:05Z","timestamp":1775731265681,"version":"3.50.1"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9207382","type":"proceedings-article","created":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T20:40:33Z","timestamp":1601412033000},"page":"1-8","source":"Crossref","is-referenced-by-count":38,"title":["Scaling Active Inference"],"prefix":"10.1109","author":[{"given":"Alexander","family":"Tschantz","sequence":"first","affiliation":[]},{"given":"Manuel","family":"Baltieri","sequence":"additional","affiliation":[]},{"given":"Anil. K.","family":"Seth","sequence":"additional","affiliation":[]},{"given":"Christopher L.","family":"Buckley","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Nonparametric entropy estimation: An overview","volume":"6","author":"beirlant","year":"1997","journal-title":"International Journal of Mathematical and Statistical Sciences"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.41703"},{"key":"ref33","article-title":"Whence the Expected Free Energyƒ","author":"millidge","year":"2020"},{"key":"ref32","article-title":"Reinforcement Learning through Active Inference","author":"tschantz","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007805"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-50138-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2008.09.007"},{"key":"ref35","first-page":"5","article-title":"Active sensing in the categorization of visual patterns","author":"yang","year":"2019","journal-title":"Elife"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01102"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3115.003.0030"},{"key":"ref62","article-title":"A survey on intrinsic motivation in reinforcement learning","author":"aubret","year":"2019"},{"key":"ref61","first-page":"206","article-title":"Exploration in model-based reinforcement learning by empirically estimating learning progress","volume":"25","author":"lopes","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s12064-011-0142-z"},{"key":"ref28","article-title":"Model Predictive Control","author":"camacho","year":"2007","journal-title":"Advanced Textbooks in Control and Signal Processing"},{"key":"ref64","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","author":"mohamed","year":"2015"},{"key":"ref27","author":"depeweg","year":"2017","journal-title":"Decomposition of uncertainty for active learning and reliable reinforcement learning in stochastic systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.05.002"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728069"},{"key":"ref29","article-title":"Bootstrapping the expressivity with model-based planning","author":"dong","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22887-2_5"},{"key":"ref68","article-title":"Approximate bayesian inference in spatial environments","author":"mirchev","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.07.012"},{"key":"ref2","article-title":"Recurrent world models facilitate¨ policy evolution","author":"ha","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/e21030257"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2017.09.004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2008.0300"},{"key":"ref24","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X12000477"},{"key":"ref26","article-title":"Decomposition of uncertainty in bayesian deep learning for efficient and risk-sensitive learning","author":"depeweg","year":"2017"},{"key":"ref25","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015"},{"key":"ref50","article-title":"Uncertainty-aware model-based policy optimization","author":"vuong","year":"2019"},{"key":"ref51","article-title":"Bayesian inference with anchored ensembles of neural networks, and application to exploration in reinforcement learning","author":"pearce","year":"2018"},{"key":"ref59","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","volume":"17","author":"chentanez","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref58","author":"thrun","year":"1992","journal-title":"Efficient exploration in reinforcement learning"},{"key":"ref57","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015"},{"key":"ref56","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016"},{"key":"ref55","article-title":"Generalization and exploration via randomized value functions","author":"osband","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12145"},{"key":"ref53","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","author":"agrawal","year":"2012"},{"key":"ref52","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/17588928.2015.1020053"},{"key":"ref40","article-title":"VIME: Variational information maximizing exploration","author":"houthooft","year":"2016"},{"key":"ref12","author":"friston","year":"2019","journal-title":"A free energy principle for a particular physics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00999"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2018.04.004"},{"key":"ref16","article-title":"Deep active inference as variational policy gradients","author":"millidge","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-018-0785-7"},{"key":"ref18","article-title":"Bayesian policy selection using active inference","author":"c\u00b8atal","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref4","article-title":"Mastering atari, go, chess and shogi by planning with a learned model","author":"schrittwieser","year":"2019"},{"key":"ref3","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018"},{"key":"ref6","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2018"},{"key":"ref5","first-page":"5779","article-title":"Model-based´ active exploration","author":"shyam","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Making the world differentiable: On using self-supervised fully recurrent neural networks for dynamic reinforcement learning and planning in non-stationary environments","author":"schmidhuber","year":"1990"},{"key":"ref49","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"kahn","year":"2017"},{"key":"ref7","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"28th International Conference on Machine Learning (ICML11)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2787"},{"key":"ref46","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015"},{"key":"ref45","article-title":"Model-based reinforcement learning for atari","author":"kaiser","year":"2019"},{"key":"ref48","article-title":"Improving PILCO with bayesian neural network dynamics models","author":"gal","year":"2016","journal-title":"Data-Efficient Machine Learning workshop"},{"key":"ref47","article-title":"Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning","author":"nagabandi","year":"2017"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2019"},{"key":"ref41","article-title":"Information maximizing exploration with a latent dynamics model","author":"barron","year":"2018"},{"key":"ref44","article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","author":"karl","year":"2016"},{"key":"ref43","article-title":"Deep variational reinforcement learning for POMDPs","author":"igl","year":"2018"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","location":"Glasgow, United Kingdom","start":{"date-parts":[[2020,7,19]]},"end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09207382.pdf?arnumber=9207382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T17:52:25Z","timestamp":1656438745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207382\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207382","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}