{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T06:00:52Z","timestamp":1783749652456,"version":"3.55.0"},"reference-count":91,"publisher":"MIT Press","issue":"5","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The free energy principle and its corollary, the active inference framework, serve as theoretical foundations in the domain of neuroscience, explaining the genesis of intelligent behavior. This principle states that the processes of perception, learning, and decision making\u2014within an agent\u2014are all driven by the objective of \u201cminimizing free energy,\u201d evincing the following behaviors: learning and employing a generative model of the environment to interpret observations, thereby achieving perception, and selecting actions to maintain a stable preferred state and minimize the uncertainty about the environment, thereby achieving decision making. This fundamental principle can be used to explain how the brain processes perceptual information, learns about the environment, and selects actions. Two pivotal tenets are that the agent employs a generative model for perception and planning and that interaction with the world (and other agents) enhances the performance of the generative model and augments perception. With the evolution of control theory and deep learning tools, agents based on the FEP have been instantiated in various ways across different domains, guiding the design of a multitude of generative models and decision-making algorithms. This letter first introduces the basic concepts of the FEP, followed by its historical development and connections with other theories of intelligence, and then delves into the specific application of the FEP to perception and decision making, encompassing both low-dimensional simple situations and high-dimensional complex situations. It compares the FEP with model-based reinforcement learning to show that the FEP provides a better objective function. We illustrate this using numerical studies of Dreamer3 by adding expected information gain into the standard objective function. In a complementary fashion, existing reinforcement learning, and deep learning algorithms can also help implement the FEP-based agents. Finally, we discuss the various capabilities that agents need to possess in complex environments and state that the FEP can aid agents in acquiring these capabilities.<\/jats:p>","DOI":"10.1162\/neco_a_01642","type":"journal-article","created":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T20:57:00Z","timestamp":1709931420000},"page":"963-1021","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":12,"title":["An Overview of the Free Energy Principle and Related Research"],"prefix":"10.1162","volume":"36","author":[{"given":"Zhengquan","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Information Science of Electromagnetic Waves, Fudan University, Shanghai, P.R.C. zqzhang22@m.fudan.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Information Science of Electromagnetic Waves, Fudan University, Shanghai, P.R.C. fengxu@fudan.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2024,4,23]]},"reference":[{"issue":"3","key":"2024042423252866200_bib1","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s00429-012-0475-5","article-title":"Predictions not commands: Active inference in the motor system","volume":"218","author":"Adams","year":"2013","journal-title":"Brain Structure and Function"},{"issue":"6","key":"2024042423252866200_bib2","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: A brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Processing Magazine"},{"key":"2024042423252866200_bib3","first-page":"4665","article-title":"Active inference for integrated state-estimation, control, and learning","volume-title":"Proceedings of the 2021 IEEE International Conference on Robotics and Automation","author":"Baioumy","year":"2021"},{"key":"2024042423252866200_bib4","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.23919\/ECC54610.2021.9654913","article-title":"Fault-tolerant control of robot manipulators with sensory faults using unbiased active inference","volume-title":"Proceedings of the 2021 European Control Conference","author":"Baioumy","year":"2021"},{"issue":"3","key":"2024042423252866200_bib5","doi-asserted-by":"publisher","first-page":"257","DOI":"10.3390\/e21030257","article-title":"PID control as a process of active inference with linear generative models","volume":"21","author":"Baltieri","year":"2019","journal-title":"Entropy"},{"key":"2024042423252866200_bib6","article-title":"On Kalman-Bucy filters, linear quadratic control & active inference","author":"Baltieri","year":"2020"},{"key":"2024042423252866200_bib7","author":"Bengio","year":"2019","journal-title":"The consciousness prior"},{"issue":"518","key":"2024042423252866200_bib8","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational inference: A review for statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"Journal of the American Statistical Association"},{"key":"2024042423252866200_bib9","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.jmp.2015.11.003","article-title":"A tutorial on the free-energy framework for modelling perception and learning","volume":"76","author":"Bogacz","year":"2017","journal-title":"Journal of Mathematical Psychology"},{"issue":"1","key":"2024042423252866200_bib10","first-page":"69","article-title":"Markov chain Monte Carlo method and its application","volume":"47","author":"Brooks","year":"1998","journal-title":"Journal of the Royal Statistical Society: Series D"},{"key":"2024042423252866200_bib11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jmp.2017.09.004","article-title":"The free energy principle for action and perception: A mathematical review","volume":"81","author":"Buckley","year":"2017","journal-title":"Journal of Mathematical Psychology"},{"issue":"4","key":"2024042423252866200_bib12","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1080\/09515089.2015.1135238","article-title":"The body as laboratory: Prediction-error minimization, embodiment, and representation","volume":"29","author":"Burr","year":"2016","journal-title":"Philosophical Psychology"},{"key":"2024042423252866200_bib13","author":"\u00c7atal","year":"2019","journal-title":"Bayesian policy selection using active inference"},{"key":"2024042423252866200_bib14","first-page":"3952","article-title":"Learning perception and planning with deep active inference","volume-title":"Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Catal","year":"2020"},{"key":"2024042423252866200_bib15","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.neunet.2021.05.010","article-title":"Robot navigation as hierarchical active inference","volume":"142","author":"\u00c7atal","year":"2021","journal-title":"Neural Networks"},{"key":"2024042423252866200_bib16","doi-asserted-by":"crossref","first-page":"574372","DOI":"10.3389\/fncom.2020.574372","article-title":"Learning generative state space models for active inference","volume":"14","author":"\u00c7atal","year":"2020","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"5","key":"2024042423252866200_bib17","doi-asserted-by":"publisher","first-page":"1402","DOI":"10.1162\/neco_a_01383","article-title":"Predictive processing in cognitive robotics: A review","volume":"33","author":"Ciria","year":"2021","journal-title":"Neural Computation"},{"issue":"48","key":"2024042423252866200_bib18","doi-asserted-by":"publisher","first-page":"30055","DOI":"10.1073\/pnas.1912789117","article-title":"The frontier of simulation-based inference","volume":"117","author":"Cranmer","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"9","key":"2024042423252866200_bib19","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1016\/j.bpsc.2018.06.010","article-title":"Active inference in OpenAI Gym: A paradigm for computational investigations into psychiatric illness","volume":"3","author":"Cullen","year":"2018","journal-title":"Biological Psychiatry: Cognitive Neuroscience and Neuroimaging"},{"key":"2024042423252866200_bib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2020.102447","article-title":"Active inference on discrete state-spaces: A synthesis","volume":"99","author":"Da Costa","year":"2020","journal-title":"Journal of Mathematical Psychology"},{"issue":"8","key":"2024042423252866200_bib21","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1167\/jov.20.8.22","article-title":"A dual foveal-peripheral visual processing model implements efficient saccade selection","volume":"20","author":"Dauc\u00e9","year":"2020","journal-title":"Journal of Vision"},{"key":"2024042423252866200_bib22","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/978-3-030-64919-7_17","article-title":"Visual search as active inference","volume-title":"Active inference","author":"Dauc\u00e9","year":"2020"},{"issue":"5","key":"2024042423252866200_bib23","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1162\/neco.1995.7.5.889","article-title":"The Helmholtz machine","volume":"7","author":"Dayan","year":"1995","journal-title":"Neural Computation"},{"issue":"1","key":"2024042423252866200_bib24","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1038\/s42256-021-00433-9","article-title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","volume":"4","author":"Eppe","year":"2022","journal-title":"Nature Machine Intelligence"},{"key":"2024042423252866200_bib25","author":"Ferraro","year":"2022","journal-title":"Disentangling shape and pose for object-centric deep active inference models"},{"key":"2024042423252866200_bib26","first-page":"11662","article-title":"Deep active inference agents using Monte-Carlo methods","volume-title":"Advances in neural information processing systems","author":"Fountas","year":"2020"},{"issue":"9","key":"2024042423252866200_bib27","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1016\/j.neunet.2003.06.005","article-title":"Learning and inference in the brain","volume":"16","author":"Friston","year":"2003","journal-title":"Neural Networks"},{"issue":"11","key":"2024042423252866200_bib28","doi-asserted-by":"publisher","first-page":"e1000211","DOI":"10.1371\/journal.pcbi.1000211","article-title":"Hierarchical models in the brain","volume":"4","author":"Friston","year":"2008","journal-title":"PLOS Computational Biology"},{"issue":"8","key":"2024042423252866200_bib29","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1038\/nrn2787-c2","article-title":"Is the free-energy principle neurocentric?","volume":"11","author":"Friston","year":"2010","journal-title":"Nature Reviews Neuroscience"},{"key":"2024042423252866200_bib30","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2012.00151","article-title":"Perceptions as hypotheses: Saccades as experiments","volume":"3","author":"Friston","year":"2012","journal-title":"Frontiers in Psychology"},{"issue":"3","key":"2024042423252866200_bib31","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1162\/neco_a_01351","article-title":"Sophisticated inference","volume":"33","author":"Friston","year":"2021","journal-title":"Neural Computation"},{"issue":"7","key":"2024042423252866200_bib32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0006421","article-title":"Reinforcement learning or active inference?","volume":"4","author":"Friston","year":"2009","journal-title":"PLOS One"},{"issue":"1","key":"2024042423252866200_bib33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/NECO_a_00912","article-title":"Active inference: A process theory","volume":"29","author":"Friston","year":"2017","journal-title":"Neural Computation"},{"issue":"1521","key":"2024042423252866200_bib34","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1098\/rstb.2008.0300","article-title":"Predictive coding under the free-energy principle","volume":"364","author":"Friston","year":"2009","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"issue":"1\u20133","key":"2024042423252866200_bib35","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.jphysparis.2006.10.001","article-title":"A free energy principle for the brain","volume":"100","author":"Friston","year":"2006","journal-title":"Journal of Physiology-Paris"},{"issue":"10","key":"2024042423252866200_bib36","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1162\/neco_a_00999","article-title":"Active inference, curiosity and insight","volume":"29","author":"Friston","year":"2017","journal-title":"Neural Computation"},{"issue":"1","key":"2024042423252866200_bib37","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.neuroimage.2006.08.035","article-title":"Variational free energy and the Laplace approximation","volume":"34","author":"Friston","year":"2007","journal-title":"NeuroImage"},{"issue":"4","key":"2024042423252866200_bib38","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1162\/NETN_a_00018","article-title":"The graphical brain: Belief propagation and active inference","volume":"1","author":"Friston","year":"2017","journal-title":"Network Neuroscience"},{"key":"2024042423252866200_bib39","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1016\/j.neubiorev.2018.04.004","article-title":"Deep temporal models and active inference","volume":"90","author":"Friston","year":"2018","journal-title":"Neuroscience and Biobehavioral Reviews"},{"key":"2024042423252866200_bib40","author":"Gershman","year":"2019","journal-title":"What does the free energy principle tell us about the brain?"},{"key":"2024042423252866200_bib41","author":"Hafner","year":"2022","journal-title":"Mastering Atari with discrete world models"},{"key":"2024042423252866200_bib42","author":"Hafner","year":"2023","journal-title":"Mastering diverse domains through world models."},{"key":"2024042423252866200_bib43","first-page":"9474","article-title":"Neural-Sim: Augmenting differentiable simulators with neural networks","volume-title":"Proceedings of the 2021 IEEE International Conference on Robotics and Automation","author":"Heiden","year":"2021"},{"key":"2024042423252866200_bib44","doi-asserted-by":"crossref","DOI":"10.21105\/joss.04098","article-title":"Pymdp: A Python library for active inference in discrete state spaces","author":"Heins","year":"2022"},{"key":"2024042423252866200_bib45","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.509354","article-title":"Deep active inference and scene construction","volume":"3","author":"Heins","year":"2020","journal-title":"Frontiers in Artificial Intelligence"},{"issue":"2","key":"2024042423252866200_bib46","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1111\/nous.12062","article-title":"The self-evidencing brain","volume":"50","author":"Hohwy","year":"2016","journal-title":"No\u00fbs"},{"key":"2024042423252866200_bib47","article-title":"Experimental validation of the free-energy principle with in vitro neural networks","volume":"14","author":"Isomura","year":"2022","journal-title":"Nature Communications"},{"issue":"23","key":"2024042423252866200_bib48","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1016\/j.neuron.2022.09.001","article-title":"In vitro neurons learn and exhibit sentience when embodied in a simulated game-world. Preprint, Synthetic Biology","volume":"110","author":"Kagan","year":"2021","journal-title":"Neuron"},{"key":"2024042423252866200_bib49","author":"Kingma","year":"2014","journal-title":"Auto-encoding variational Bayes."},{"issue":"12","key":"2024042423252866200_bib50","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1016\/j.tins.2004.10.007","article-title":"The Bayesian brain: The role of uncertainty in neural coding and computation","volume":"27","author":"Knill","year":"2004","journal-title":"Trends in Neurosciences"},{"key":"2024042423252866200_bib51","author":"Lanillos","year":"2021","journal-title":"Active inference in robotics and artificial agents: Survey and challenges."},{"issue":"5","key":"2024042423252866200_bib52","doi-asserted-by":"publisher","first-page":"564","DOI":"10.3390\/e22050564","article-title":"Goal-directed planning for habituated agents by active inference using a variational recurrent neural network","volume":"22","author":"Matsumoto","year":"2020","journal-title":"Entropy"},{"issue":"2","key":"2024042423252866200_bib53","doi-asserted-by":"publisher","first-page":"301","DOI":"10.3390\/e24020301","article-title":"The free energy principle for perception and action: A deep learning perspective","volume":"24","author":"Mazzaglia","year":"2022","journal-title":"Entropy"},{"key":"2024042423252866200_bib54","article-title":"Contrastive active inference","volume-title":"Advances in neural information processing systems","author":"Mazzaglia","year":"2021"},{"key":"2024042423252866200_bib55","doi-asserted-by":"crossref","DOI":"10.1109\/IROS51168.2021.9636394","article-title":"Multimodal VAE active inference controller","author":"Meo","year":"2021"},{"key":"2024042423252866200_bib56","doi-asserted-by":"publisher","first-page":"102348","DOI":"10.1016\/j.jmp.2020.102348","article-title":"Deep Active Inference as Variational Policy Gradients","volume":"96","author":"Millidge","year":"2019","journal-title":"Journal of Mathematical Psychology"},{"key":"2024042423252866200_bib57","author":"Millidge","year":"2022"},{"key":"2024042423252866200_bib58","author":"Moerland","year":"2022","journal-title":"Model-based reinforcement learning: A survey."},{"issue":"4","key":"2024042423252866200_bib59","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1109\/TNNLS.2015.2492140","article-title":"Learning to perceive the world as probabilistic or deterministic via interaction with others: A neuro-robotics experiment","volume":"28","author":"Murata","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"11","key":"2024042423252866200_bib60","doi-asserted-by":"publisher","first-page":"e0277199","DOI":"10.1371\/journal.pone.0277199","article-title":"Structure learning enhances concept formation in synthetic active inference agents","volume":"17","author":"Neacsu","year":"2022","journal-title":"PLOS One"},{"issue":"2","key":"2024042423252866200_bib61","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TCDS.2021.3049907","article-title":"An empirical study of active inference on a humanoid robot","volume":"14","author":"Oliver","year":"2022","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"2024042423252866200_bib62","doi-asserted-by":"publisher","first-page":"651432","DOI":"10.3389\/fnbot.2021.651432","article-title":"Generative models for active vision","volume":"15","author":"Parr","year":"2021","journal-title":"Frontiers in Neurorobotics"},{"key":"2024042423252866200_bib63","volume-title":"Causality: Models, reasoning, and inference.","author":"Pearl","year":"2000"},{"key":"2024042423252866200_bib64","volume-title":"The book of why: The new science of cause and effect","author":"Pearl","year":"2018"},{"issue":"2","key":"2024042423252866200_bib65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TRO.2022.3226144","article-title":"Active inference and behavior trees for reactive action planning and execution in robotics","volume":"39","author":"Pezzato","year":"2023","journal-title":"IEEE Transactions on Robotics"},{"issue":"2","key":"2024042423252866200_bib66","doi-asserted-by":"publisher","first-page":"2973","DOI":"10.1109\/LRA.2020.2974451","article-title":"A novel adaptive controller for robot manipulators based on active inference","volume":"5","author":"Pezzato","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"3","key":"2024042423252866200_bib67","doi-asserted-by":"publisher","first-page":"20220029","DOI":"10.1098\/rsfs.2022.0029","article-title":"On Bayesian mechanics: A physics of and by beliefs","volume":"13","author":"Ramstead","year":"2023","journal-title":"Interface Focus"},{"issue":"1","key":"2024042423252866200_bib68","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1038\/4580","article-title":"Predictive coding in the visual cortex: A functional interpretation of some extra-classical receptive-field effects","volume":"2","author":"Rao","year":"1999","journal-title":"Nature Neuroscience"},{"key":"2024042423252866200_bib69","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/978-3-030-64919-7_10","article-title":"A deep active inference model of the rubber-hand illusion","volume":"1326","author":"Rood","year":"2020","journal-title":"Communications in Computer and Information Science"},{"key":"2024042423252866200_bib70","article-title":"Dynamic routing between capsules","volume-title":"Advances in neural information processing systems","author":"Sabour","year":"2017"},{"issue":"3","key":"2024042423252866200_bib71","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1162\/neco_a_01357","article-title":"Active inference: Demystified and compared","volume":"33","author":"Sajid","year":"2021","journal-title":"Neural Computation"},{"key":"2024042423252866200_bib72","author":"Sajid","year":"2021","journal-title":"Exploration and preference satisfaction trade-off in reward-free learning."},{"key":"2024042423252866200_bib73","first-page":"1","article-title":"End-to-end pixel-based deep active inference for body perception and action","volume-title":"Proceedings of the 2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics","author":"Sancaktar","year":"2020"},{"key":"2024042423252866200_bib74","first-page":"29246","article-title":"Clockwork variational autoencoders","volume-title":"Advances in neural information processing systems","author":"Saxena","year":"2021"},{"issue":"5","key":"2024042423252866200_bib75","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/JPROC.2021.3058954","article-title":"Toward causal representation learning","volume":"109","author":"Scholk\u00f6pf","year":"2021","journal-title":"Proceedings of the IEEE"},{"key":"2024042423252866200_bib76","doi-asserted-by":"crossref","DOI":"10.31234\/osf.io\/b4jm6","volume-title":"A step-by-step tutorial on active inference and its application to empirical data.","author":"Smith","year":"2021"},{"key":"2024042423252866200_bib77","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2020.00041","article-title":"An active inference approach to modeling structure learning: Concept learning as an example case","volume":"14","author":"Smith","year":"2020","journal-title":"Frontiers in Computational Neuroscience"},{"key":"2024042423252866200_bib78","author":"Toth","year":"2020","journal-title":"Hamiltonian generative networks."},{"key":"2024042423252866200_bib79","first-page":"1","article-title":"Scaling active inference","volume-title":"Proceedings of the 2020 International Joint Conference on Neural Networks","author":"Tschantz","year":"2019"},{"key":"2024042423252866200_bib80","author":"Tschantz","year":"2020","journal-title":"Reinforcement learning through active inference"},{"issue":"6","key":"2024042423252866200_bib81","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1007\/s00422-018-0785-7","article-title":"Deep active inference","volume":"112","author":"Ueltzh\u00f6ffer","year":"2018","journal-title":"Biological Cybernetics"},{"key":"2024042423252866200_bib82","article-title":"Object-based active inference","volume":"1721","author":"van Bergen","year":"2022","journal-title":"Communications in Computer and Information Science"},{"key":"2024042423252866200_bib83","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-030-64919-7_11","article-title":"You only look as much as you have to: Using the free energy principle for active vision","volume-title":"Active inference","author":"Van de Maele","year":"2020"},{"key":"2024042423252866200_bib84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71214-3","article-title":"Disentangling what and where for 3D object-centric representations through active inference","volume":"1524","author":"Van de Maele","year":"2021","journal-title":"Communications in Computer and Information Science"},{"key":"2024042423252866200_bib85","author":"Van de Maele","year":"2023","journal-title":"Object-centric scene representations using active inference. found?"},{"key":"2024042423252866200_bib86","first-page":"61","article-title":"Deep active inference for partially observable MDPs","volume-title":"International Workshop on Active Inference, 1326","author":"van der Himst","year":"2020"},{"key":"2024042423252866200_bib87","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-93736-2_60","article-title":"Deep active inference for pixel-based discrete control: Evaluation on the car racing problem","volume":"1524","author":"van Hoeffelen","year":"2021","journal-title":"Communications in Computer and Information Science"},{"key":"2024042423252866200_bib88","doi-asserted-by":"publisher","first-page":"4234","DOI":"10.1109\/TSP.2021.3095711","article-title":"Application of the free energy principle to estimation and control","volume":"69","author":"van de Laar","year":"2021","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"23","key":"2024042423252866200_bib89","first-page":"661","article-title":"Variational message passing","volume":"6","author":"Winn","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"2024042423252866200_bib90","first-page":"2318","article-title":"Greedy hierarchical variational autoencoders for large-scale video prediction","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wu","year":"2021"},{"key":"2024042423252866200_bib91","author":"Yildirim","year":"2023","journal-title":"3D shape perception integrates intuitive physics and analysis-by-synthesis"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/5\/963\/2366829\/neco_a_01642.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/5\/963\/2366829\/neco_a_01642.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T23:26:13Z","timestamp":1714001173000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/36\/5\/963\/119791\/An-Overview-of-the-Free-Energy-Principle-and"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,23]]},"references-count":91,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,4,23]]},"published-print":{"date-parts":[[2024,4,23]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01642","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,5]]},"published":{"date-parts":[[2024,4,23]]}}}