{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:22:10Z","timestamp":1759332130956,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030937355"},{"type":"electronic","value":"9783030937362"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-93736-2_60","type":"book-chapter","created":{"date-parts":[[2022,2,17]],"date-time":"2022-02-17T21:02:28Z","timestamp":1645131748000},"page":"843-856","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep Active Inference for\u00a0Pixel-Based Discrete Control: Evaluation on\u00a0the\u00a0Car Racing Problem"],"prefix":"10.1007","author":[{"given":"N. T. A.","family":"van Hoeffelen","sequence":"first","affiliation":[]},{"given":"Pablo","family":"Lanillos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,17]]},"reference":[{"key":"60_CR1","unstructured":"Openai\u2019s carracing-v0 leaderboard. https:\/\/github.com\/openai\/gym\/wiki\/Leaderboard#carracing-v0"},{"key":"60_CR2","unstructured":"\u00c7atal, O., Nauta, J., Verbelen, T., Simoens, P., Dhoedt, B.: Bayesian policy selection using active inference. arXiv preprint arXiv:1904.08149 (2019)"},{"key":"60_CR3","doi-asserted-by":"publisher","first-page":"103","DOI":"10.3389\/fncom.2020.574372","volume":"14","author":"O \u00c7atal","year":"2020","unstructured":"\u00c7atal, O., Wauthier, S., De Boom, C., Verbelen, T., Dhoedt, B.: Learning generative state space models for active inference. Front. Comput. Neurosci. 14, 103 (2020)","journal-title":"Front. Comput. Neurosci."},{"key":"60_CR4","doi-asserted-by":"publisher","first-page":"102447","DOI":"10.1016\/j.jmp.2020.102447","volume":"99","author":"L Da Costa","year":"2020","unstructured":"Da Costa, L., Parr, T., Sajid, N., Veselic, S., Neacsu, V., Friston, K.: Active inference on discrete state-spaces: a synthesis. J. Math. Psychol. 99, 102447 (2020)","journal-title":"J. Math. Psychol."},{"key":"60_CR5","unstructured":"Fountas, Z., Sajid, N., Mediano, P.A., Friston, K.: Deep active inference agents using monte-carlo methods. arXiv preprint arXiv:2006.04176 (2020)"},{"issue":"1456","key":"60_CR6","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1098\/rstb.2005.1622","volume":"360","author":"K Friston","year":"2005","unstructured":"Friston, K.: A theory of cortical responses. Philos. Trans. R. Soc. B Biol. Sci. 360(1456), 815\u2013836 (2005)","journal-title":"Philos. Trans. R. Soc. B Biol. Sci."},{"issue":"8","key":"60_CR7","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s00422-012-0512-8","volume":"106","author":"K Friston","year":"2012","unstructured":"Friston, K., Samothrakis, S., Montague, R.: Active inference and agency: optimal control without cost functions. Biol. Cybern. 106(8), 523\u2013541 (2012)","journal-title":"Biol. Cybern."},{"issue":"3","key":"60_CR8","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s00422-010-0364-z","volume":"102","author":"KJ Friston","year":"2010","unstructured":"Friston, K.J., Daunizeau, J., Kilner, J., Kiebel, S.J.: Action and behavior: a free-energy formulation. Biol. Cybern. 102(3), 227\u2013260 (2010)","journal-title":"Biol. Cybern."},{"key":"60_CR9","unstructured":"Gaier, A., Ha, D.: Weight agnostic neural networks. arXiv preprint arXiv:1906.04358 (2019)"},{"key":"60_CR10","unstructured":"Ha, D., Schmidhuber, J.: World models. arXiv preprint arXiv:1803.10122 (2018)"},{"key":"60_CR11","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/978-3-030-64919-7_8","volume-title":"Active Inference","author":"O van der Himst","year":"2020","unstructured":"van der Himst, O., Lanillos, P.: Deep active inference for partially observable MDPs. In: IWAI 2020. CCIS, vol. 1326, pp. 61\u201371. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-64919-7_8"},{"key":"60_CR12","unstructured":"Khan, M., Elibol., O.: Car racing using reinforcement learning (2018). https:\/\/web.stanford.edu\/class\/cs221\/2017\/restricted\/p-final\/elibol\/final.pdf"},{"key":"60_CR13","unstructured":"Klimov, O.: Carracing-v0. https:\/\/gym.openai.com\/envs\/CarRacing-v0\/"},{"key":"60_CR14","unstructured":"Lanillos, P., van Gerven, M.: Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception. arXiv preprint arXiv:2105.04261 (2021)"},{"key":"60_CR15","unstructured":"Lin, L.: Reinforcement learning for robots using neural networks (1992)"},{"key":"60_CR16","doi-asserted-by":"crossref","unstructured":"Meo, C., Lanillos, P.: Multimodal VAE active inference controller. arXiv preprint arXiv:2103.04412 (2021)","DOI":"10.1109\/IROS51168.2021.9636394"},{"key":"60_CR17","doi-asserted-by":"publisher","first-page":"102348","DOI":"10.1016\/j.jmp.2020.102348","volume":"96","author":"B Millidge","year":"2020","unstructured":"Millidge, B.: Deep active inference as variational policy gradients. J. Math. Psychol. 96, 102348 (2020)","journal-title":"J. Math. Psychol."},{"key":"60_CR18","unstructured":"Min J. Jang, S., Lee, C.: Reinforcement car racing with a3c (2017). https:\/\/www.scribd.com\/document\/358019044\/Reinforcement-Car-Racing-with-A3C"},{"issue":"7540","key":"60_CR19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"60_CR20","unstructured":"Noel, A.D., van Hoof, C., Millidge, B.: Online reinforcement learning with sparse rewards through an active inference capsule. arXiv preprint arXiv:2106.02390 (2021)"},{"issue":"5","key":"60_CR21","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s00422-019-00805-w","volume":"113","author":"T Parr","year":"2019","unstructured":"Parr, T., Friston, K.J.: Generalised free energy and active inference. Biol. Cybern. 113(5), 495\u2013513 (2019)","journal-title":"Biol. Cybern."},{"key":"60_CR22","doi-asserted-by":"crossref","unstructured":"Risi, S., Stanley, K.O.: Deep neuroevolution of recurrent and discrete world models. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 456\u2013462 (2019)","DOI":"10.1145\/3321707.3321817"},{"key":"60_CR23","doi-asserted-by":"crossref","unstructured":"Sancaktar, C., van Gerven, M.A., Lanillos, P.: End-to-end pixel-based deep active inference for body perception and action. In: 2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/ICDL-EpiRob48136.2020.9278105"},{"key":"60_CR24","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.41703","volume":"8","author":"P Schwartenbeck","year":"2019","unstructured":"Schwartenbeck, P., Passecker, J., Hauser, T.U., FitzGerald, T.H., Kronbichler, M., Friston, K.J.: Computational mechanisms of curiosity and goal-directed exploration. Elife 8, e41703 (2019)","journal-title":"Elife"},{"key":"60_CR25","unstructured":"Slik, J.: Deep reinforcement learning for end-to-end autonomous driving (2019)"},{"key":"60_CR26","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"60_CR27","doi-asserted-by":"crossref","unstructured":"Tschantz, A., Baltieri, M., Seth, A.K., Buckley, C.L.: Scaling active inference. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207382"},{"key":"60_CR28","unstructured":"Tschantz, A., Millidge, B., Seth, A.K., Buckley, C.L.: Reinforcement learning through active inference. arXiv preprint arXiv:2002.12636 (2020)"},{"issue":"6","key":"60_CR29","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/s00422-018-0785-7","volume":"112","author":"K Ueltzh\u00f6ffer","year":"2018","unstructured":"Ueltzh\u00f6ffer, K.: Deep active inference. Biol. Cybern. 112(6), 547\u2013573 (2018)","journal-title":"Biol. Cybern."},{"key":"60_CR30","unstructured":"van der Wal, D., Intelligentie, B.O.K., Shang, W.: Advantage actor-critic methods for carracing (2018)"},{"key":"60_CR31","unstructured":"Zhang, Y.: Deep reinforcement learning with mixed convolutional network. arXiv preprint arXiv:2010.00717 (2020)"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-93736-2_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T02:18:29Z","timestamp":1651803509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-93736-2_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030937355","9783030937362"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-93736-2_60","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"869","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"210","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}