{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T10:54:17Z","timestamp":1775732057335,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"IITB-Monash Research Academy, Mumbai","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}]},{"name":"IITB-Monash Research Academy, Mumbai","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}]},{"name":"IITB-Monash Research Academy, Mumbai","award":["DP200100757"],"award-info":[{"award-number":["DP200100757"]}]},{"name":"IITB-Monash Research Academy, Mumbai","award":["1194910"],"award-info":[{"award-number":["1194910"]}]},{"name":"IITB-Monash Research Academy, Mumbai","award":["203147\/Z\/16\/Z"],"award-info":[{"award-number":["203147\/Z\/16\/Z"]}]},{"name":"Department of Biotechnology, Government of India","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}]},{"name":"Department of Biotechnology, Government of India","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}]},{"name":"Department of Biotechnology, Government of India","award":["DP200100757"],"award-info":[{"award-number":["DP200100757"]}]},{"name":"Department of Biotechnology, Government of India","award":["1194910"],"award-info":[{"award-number":["1194910"]}]},{"name":"Department of Biotechnology, Government of India","award":["203147\/Z\/16\/Z"],"award-info":[{"award-number":["203147\/Z\/16\/Z"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["DP200100757"],"award-info":[{"award-number":["DP200100757"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["1194910"],"award-info":[{"award-number":["1194910"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["203147\/Z\/16\/Z"],"award-info":[{"award-number":["203147\/Z\/16\/Z"]}]},{"name":"Japan Science and Technology Agency (JST) CREST","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}]},{"name":"Japan Science and Technology Agency (JST) CREST","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}]},{"name":"Japan Science and Technology Agency (JST) CREST","award":["DP200100757"],"award-info":[{"award-number":["DP200100757"]}]},{"name":"Japan Science and Technology Agency (JST) CREST","award":["1194910"],"award-info":[{"award-number":["1194910"]}]},{"name":"Japan Science and Technology Agency (JST) CREST","award":["203147\/Z\/16\/Z"],"award-info":[{"award-number":["203147\/Z\/16\/Z"]}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP200100757"],"award-info":[{"award-number":["DP200100757"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["1194910"],"award-info":[{"award-number":["1194910"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["203147\/Z\/16\/Z"],"award-info":[{"award-number":["203147\/Z\/16\/Z"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Australian National Health and Medical Research Council Investigator Grant","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}]},{"name":"Australian National Health and Medical Research Council Investigator Grant","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}]},{"name":"Australian National Health and Medical Research Council Investigator Grant","award":["DP200100757"],"award-info":[{"award-number":["DP200100757"]}]},{"name":"Australian National Health and Medical Research Council Investigator Grant","award":["1194910"],"award-info":[{"award-number":["1194910"]}]},{"name":"Australian National Health and Medical Research Council Investigator Grant","award":["203147\/Z\/16\/Z"],"award-info":[{"award-number":["203147\/Z\/16\/Z"]}]},{"name":"The Wellcome Centre for Human Neuroimaging","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}]},{"name":"The Wellcome Centre for Human Neuroimaging","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}]},{"name":"The Wellcome Centre for Human Neuroimaging","award":["DP200100757"],"award-info":[{"award-number":["DP200100757"]}]},{"name":"The Wellcome Centre for Human Neuroimaging","award":["1194910"],"award-info":[{"award-number":["1194910"]}]},{"name":"The Wellcome Centre for Human Neuroimaging","award":["203147\/Z\/16\/Z"],"award-info":[{"award-number":["203147\/Z\/16\/Z"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important. Active inference, regarded as a general theory of behaviour, offers a principled approach to probing the basis of sophistication in planning and decision-making. This paper examines two decision-making schemes in active inference based on \u201cplanning\u201d and \u201clearning from experience\u201d. Furthermore, we also introduce a mixed model that navigates the data complexity trade-off between these strategies, leveraging the strengths of both to facilitate balanced decision-making. We evaluate our proposed model in a challenging grid-world scenario that requires adaptability from the agent. Additionally, our model provides the opportunity to analyse the evolution of various parameters, offering valuable insights and contributing to an explainable framework for intelligent decision-making.<\/jats:p>","DOI":"10.3390\/e26060484","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T06:35:32Z","timestamp":1717137332000},"page":"484","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["On Predictive Planning and Counterfactual Learning in Active Inference"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8559-4711","authenticated-orcid":false,"given":"Aswin","family":"Paul","sequence":"first","affiliation":[{"name":"Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Clayton 3800, Australia"},{"name":"IITB-Monash Research Academy, Mumbai 400076, India"},{"name":"Department of Electrical Engineering, IIT Bombay, Mumbai 400076 , India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2960-4919","authenticated-orcid":false,"given":"Takuya","family":"Isomura","sequence":"additional","affiliation":[{"name":"Brain Intelligence Theory Unit, RIKEN Center for Brain Science, Wako, Saitama 351-0106, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9439","authenticated-orcid":false,"given":"Adeel","family":"Razi","sequence":"additional","affiliation":[{"name":"Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Clayton 3800, Australia"},{"name":"Wellcome Trust Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK"},{"name":"CIFAR Azrieli Global Scholars Program, CIFAR, Toronto, ON M5G 1M1, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2024,5,31]]},"reference":[{"key":"ref_1","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, The MIT Press. [2nd ed.]."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/nrn2787","article-title":"The free-energy principle: A unified brain theory?","volume":"11","author":"Friston","year":"2010","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102447","DOI":"10.1016\/j.jmp.2020.102447","article-title":"Active inference on discrete state-spaces: A synthesis","volume":"99","author":"Parr","year":"2020","journal-title":"J. Math. Psychol."},{"key":"ref_4","doi-asserted-by":"crossref","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 Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Millidge, B., Tschantz, A., and Buckley, C.L. (2020). Whence the Expected Free Energy?. arXiv.","DOI":"10.1162\/neco_a_01354"},{"key":"ref_6","doi-asserted-by":"crossref","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":"Netw. Neurosci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.plrev.2019.06.001","article-title":"Morphogenesis as Bayesian inference: A variational approach to pattern formation and control in complex biological systems","volume":"33","author":"Kuchling","year":"2020","journal-title":"Phys. Life Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"539726","DOI":"10.3389\/fpsyg.2020.539726","article-title":"Losing Ourselves: Active Inference, Depersonalization, and Meditation","volume":"11","author":"Deane","year":"2020","journal-title":"Front. Psychol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","article-title":"Planning and acting in partially observable stochastic domains","volume":"101","author":"Kaelbling","year":"1998","journal-title":"Artif. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning","volume":"112","author":"Sutton","year":"1999","journal-title":"Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Heins, C., Millidge, B., Demekas, D., Klein, B., Friston, K., Couzin, I., and Tschantz, A. (2022). pymdp: A Python library for active inference in discrete state spaces. arXiv.","DOI":"10.21105\/joss.04098"},{"key":"ref_12","unstructured":"Igl, M., Zintgraf, L., Le, T.A., Wood, F., and Whiteson, S. (2018). International Conference on Machine Learning, PMLR."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Paul, A., Sajid, N., Gopalkrishnan, M., and Razi, A. (2021, January 13\u201317). Active Inference for Stochastic Control. Proceedings of the Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Virtual.","DOI":"10.1007\/978-3-030-93736-2_47"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Isomura, T., Shimazaki, H., and Friston, K.J. (2022). Canonical neural networks perform active inference. Commun. Biol., 5.","DOI":"10.1038\/s42003-021-02994-2"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s00422-018-0753-2","article-title":"Planning and navigation as active inference","volume":"112","author":"Kaplan","year":"2018","journal-title":"Biol. Cybern."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Friston, K.J., Daunizeau, J., and Kiebel, S.J. (2009). Reinforcement Learning or Active Inference?. PLoS ONE, 4.","DOI":"10.1371\/journal.pone.0006421"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2100","DOI":"10.3390\/e14112100","article-title":"A Free Energy Principle for Biological Systems","volume":"14","author":"Friston","year":"2012","journal-title":"Entropy"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1162\/neco_a_01351","article-title":"Sophisticated Inference","volume":"33","author":"Friston","year":"2021","journal-title":"Neural Comput."},{"key":"ref_19","unstructured":"Paul, A., Sajid, N., Da Costa, L., and Razi, A. (2023). On efficient computation in active inference. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/ICNN.1993.298551","article-title":"Efficient learning and planning within the Dyna framework","volume":"1","author":"Peng","year":"1993","journal-title":"IEEE Int. Conf. Neural Netw."},{"key":"ref_21","unstructured":"Friston, K.J., Salvatori, T., Isomura, T., Tschantz, A., Kiefer, A., Verbelen, T., Koudahl, M.T., Paul, A., Parr, T., and Razi, A. (2023). Active Inference and Intentional Behaviour. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.1162\/neco_a_01315","article-title":"Reverse-Engineering Neural Networks to Characterize Their Cost Functions","volume":"32","author":"Isomura","year":"2020","journal-title":"Neural Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4547","DOI":"10.1038\/s41467-023-40141-z","article-title":"Experimental validation of the free-energy principle with in vitro neural networks","volume":"14","author":"Isomura","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_24","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., and Zaremba, W. (2016). Openai gym. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","article-title":"Neuronlike adaptive elements that can solve difficult learning control problems","volume":"SMC-13","author":"Barto","year":"1983","journal-title":"IEEE Trans. Syst. Man. Cybern."},{"key":"ref_26","first-page":"5","article-title":"Multi-task Reinforcement Learning in Partially Observable Stochastic Environments","volume":"10","author":"Li","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.neunet.2022.03.021","article-title":"Exploration in neo-Hebbian reinforcement learning: Computational approaches to the exploration\u2013exploitation balance with bio-inspired neural networks","volume":"151","author":"Triche","year":"2022","journal-title":"Neural Netw."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e1424","DOI":"10.1002\/widm.1424","article-title":"Explainable artificial intelligence: An analytical review","volume":"11","author":"Angelov","year":"2021","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_29","unstructured":"Das, A., and Rad, P. (2020). Opportunities and challenges in explainable artificial intelligence (xai): A survey. arXiv, Available online: https:\/\/arxiv.org\/abs\/2006.11371."},{"key":"ref_30","unstructured":"Albarracin, M., Hip\u00f3lito, I., Tremblay, S.E., Fox, J.G., Ren\u00e9, G., Friston, K., and Ramstead, M.J. (2023). International Workshop on Active Inference, Springer Nature Switzerland."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1007\/s00422-018-0785-7","article-title":"Deep active inference","volume":"112","year":"2018","journal-title":"Biol. Cybern."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s11571-012-9220-2","article-title":"A hybrid model for the neural representation of complex mental processing in the human brain","volume":"7","author":"Fehr","year":"2013","journal-title":"Cogn. Neurodyn."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Da Costa, L., Lanillos, P., Sajid, N., Friston, K., and Khan, S. (2022). How Active Inference Could Help Revolutionise Robotics. Entropy, 24.","DOI":"10.3390\/e24030361"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1080\/17517571003763380","article-title":"On the principle of design of resilient systems \u2013 application to enterprise information systems","volume":"4","author":"Zhang","year":"2010","journal-title":"Enterp. Inf. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1109\/JSYST.2014.2339552","article-title":"Measuring the Resilience of Supply Chain Systems Using a Survival Model","volume":"9","author":"Raj","year":"2015","journal-title":"IEEE Syst. J."},{"key":"ref_36","unstructured":"Fountas, Z., Sajid, N., Mediano, P.A.M., and Friston, K. (2020). Deep Active Inference Agents Using Monte-Carlo Methods. arXiv."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/26\/6\/484\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:51:45Z","timestamp":1760107905000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/26\/6\/484"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,31]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["e26060484"],"URL":"https:\/\/doi.org\/10.3390\/e26060484","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,31]]}}}