{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T19:40:35Z","timestamp":1757706035334,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031287183"},{"type":"electronic","value":"9783031287190"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-28719-0_9","type":"book-chapter","created":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T18:03:51Z","timestamp":1679421831000},"page":"130-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["World Model Learning from\u00a0Demonstrations with\u00a0Active Inference: Application to\u00a0Driving Behavior"],"prefix":"10.1007","author":[{"given":"Ran","family":"Wei","sequence":"first","affiliation":[]},{"given":"Alfredo","family":"Garcia","sequence":"additional","affiliation":[]},{"given":"Anthony","family":"McDonald","sequence":"additional","affiliation":[]},{"given":"Gustav","family":"Markkula","sequence":"additional","affiliation":[]},{"given":"Johan","family":"Engstr\u00f6m","sequence":"additional","affiliation":[]},{"given":"Isaac","family":"Supeene","sequence":"additional","affiliation":[]},{"given":"Matthew","family":"O\u2019Kelly","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,22]]},"reference":[{"key":"9_CR1","unstructured":"Baker, C., Saxe, R., Tenenbaum, J.: Bayesian theory of mind: modeling joint belief-desire attribution. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 33 (2011)"},{"key":"9_CR2","unstructured":"Bhattacharyya, R., et al.: Modeling human driving behavior through generative adversarial imitation learning. arXiv preprint arXiv:2006.06412 (2020)"},{"key":"9_CR3","doi-asserted-by":"publisher","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":"9_CR4","unstructured":"De Haan, P., Jayaraman, D., Levine, S.: Causal confusion in imitation learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"2","key":"9_CR5","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1080\/1463922X.2017.1306148","volume":"19","author":"J Engstr\u00f6m","year":"2018","unstructured":"Engstr\u00f6m, J., et al.: Great expectations: a predictive processing account of automobile driving. Theor. Issues Ergon. Sci. 19(2), 156\u2013194 (2018)","journal-title":"Theor. Issues Ergon. Sci."},{"issue":"1","key":"9_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/NECO_a_00912","volume":"29","author":"K Friston","year":"2017","unstructured":"Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., Pezzulo, G.: Active inference: a process theory. Neural Comput. 29(1), 1\u201349 (2017)","journal-title":"Neural Comput."},{"key":"9_CR7","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"9_CR8","unstructured":"Janner, M., Fu, J., Zhang, M., Levine, S.: When to trust your model: model-based policy optimization. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"9_CR9","unstructured":"Karkus, P., Hsu, D., Lee, W.S.: QMDP-Net: deep learning for planning under partial observability. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"9_CR10","doi-asserted-by":"publisher","DOI":"10.3389\/fnrgo.2021.718699","volume":"2","author":"T Kujala","year":"2021","unstructured":"Kujala, T., Lappi, O.: Inattention and uncertainty in the predictive brain. Front. Neuroergon. 2, 718699 (2021)","journal-title":"Front. Neuroergon."},{"key":"9_CR11","unstructured":"Kwon, M., Daptardar, S., Schrater, P.R., Pitkow, X.: Inverse rational control with partially observable continuous nonlinear dynamics. In: Advances in Neural Information Processing Systems, vol. 33, pp. 7898\u20137909 (2020)"},{"key":"9_CR12","unstructured":"Lambert, N., Amos, B., Yadan, O., Calandra, R.: Objective mismatch in model-based reinforcement learning. arXiv preprint arXiv:2002.04523 (2020)"},{"key":"9_CR13","unstructured":"Leurent, E.: An environment for autonomous driving decision-making. https:\/\/github.com\/eleurent\/highway-env (2018)"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Littman, M.L., Cassandra, A.R., Kaelbling, L.P.: Learning policies for partially observable environments: scaling up. In: Machine Learning Proceedings 1995, pp. 362\u2013370. Elsevier (1995)","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"key":"9_CR15","unstructured":"Makino, T., Takeuchi, J.: Apprenticeship learning for model parameters of partially observable environments. arXiv preprint arXiv:1206.6484 (2012)"},{"issue":"3","key":"9_CR16","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/s00422-017-0743-9","volume":"112","author":"G Markkula","year":"2018","unstructured":"Markkula, G., Boer, E., Romano, R., Merat, N.: Sustained sensorimotor control as intermittent decisions about prediction errors: computational framework and application to ground vehicle steering. Biol. Cybern. 112(3), 181\u2013207 (2018)","journal-title":"Biol. Cybern."},{"key":"9_CR17","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.aap.2016.07.007","volume":"95","author":"G Markkula","year":"2016","unstructured":"Markkula, G., Engstr\u00f6m, J., Lodin, J., B\u00e4rgman, J., Victor, T.: A farewell to brake reaction times? kinematics-dependent brake response in naturalistic rear-end emergencies. Accid. Anal. Prev. 95, 209\u2013226 (2016)","journal-title":"Accid. Anal. Prev."},{"issue":"4","key":"9_CR18","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1177\/0018720819829572","volume":"61","author":"AD McDonald","year":"2019","unstructured":"McDonald, A.D., et al.: Toward computational simulations of behavior during automated driving takeovers: a review of the empirical and modeling literatures. Hum. Factors 61(4), 642\u2013688 (2019)","journal-title":"Hum. Factors"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J.: Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)","DOI":"10.21105\/joss.00861"},{"key":"9_CR20","unstructured":"Ng, A.Y., Russell, S.J., et al.: Algorithms for inverse reinforcement learning. In: Icml, vol. 1, p. 2 (2000)"},{"issue":"2153","key":"9_CR21","doi-asserted-by":"publisher","first-page":"20120683","DOI":"10.1098\/rspa.2012.0683","volume":"469","author":"PA Ortega","year":"2013","unstructured":"Ortega, P.A., Braun, D.A.: Thermodynamics as a theory of decision-making with information-processing costs. Proc. R. Soc. A: Math. Phys. Eng. Sci. 469(2153), 20120683 (2013)","journal-title":"Proc. R. Soc. A: Math. Phys. Eng. Sci."},{"key":"9_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2300000053","volume":"7","author":"T Osa","year":"2018","unstructured":"Osa, T., Pajarinen, J., Neumann, G., Bagnell, J.A., Abbeel, P., Peters, J.: An algorithmic perspective on imitation learning. Found. Trends Rob. 7, 1\u2013179 (2018)","journal-title":"Found. Trends Rob."},{"key":"9_CR23","unstructured":"Reddy, S., Dragan, A., Levine, S.: Where do you think you\u2019re going?: inferring beliefs about dynamics from behavior. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"9_CR24","unstructured":"Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 627\u2013635. JMLR Workshop and Conference Proceedings (2011)"},{"issue":"10","key":"9_CR25","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1068\/p5343","volume":"33","author":"DD Salvucci","year":"2004","unstructured":"Salvucci, D.D., Gray, R.: A two-point visual control model of steering. Perception 33(10), 1233\u20131248 (2004)","journal-title":"Perception"},{"issue":"2","key":"9_CR26","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.mehy.2014.12.007","volume":"84","author":"P Schwartenbeck","year":"2015","unstructured":"Schwartenbeck, P., et al.: Optimal inference with suboptimal models: addiction and active Bayesian inference. Med. Hypotheses 84(2), 109\u2013117 (2015)","journal-title":"Med. Hypotheses"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Tamar, A., Wu, Y., Thomas, G., Levine, S., Abbeel, P.: Value iteration networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)","DOI":"10.24963\/ijcai.2017\/700"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Tishby, N., Polani, D.: Information Theory of Decisions and Actions, pp. 601\u2013636. Springer, New York (2011)","DOI":"10.1007\/978-1-4419-1452-1_19"},{"key":"9_CR29","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"},{"issue":"4","key":"9_CR30","doi-asserted-by":"publisher","first-page":"e1007805","DOI":"10.1371\/journal.pcbi.1007805","volume":"16","author":"A Tschantz","year":"2020","unstructured":"Tschantz, A., Seth, A.K., Buckley, C.L.: Learning action-oriented models through active inference. PLoS Comput. Biol. 16(4), e1007805 (2020)","journal-title":"PLoS Comput. Biol."},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Wei, R., McDonald, A.D., Garcia, A., Alambeigi, H.: Modeling driver responses to automation failures with active inference. IEEE Trans. Intell. Transp. Syst. (2022)","DOI":"10.1109\/TITS.2022.3155381"},{"key":"9_CR32","unstructured":"Zhan, W., et al.: Interaction dataset: an international, adversarial and cooperative motion dataset in interactive driving scenarios with semantic maps. arXiv preprint arXiv:1910.03088 (2019)"},{"key":"9_CR33","unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., Dey, A.K., et al.: Maximum entropy inverse reinforcement learning. In: AAAI, vol. 8, pp. 1433\u20131438. Chicago, IL, USA (2008)"}],"container-title":["Communications in Computer and Information Science","Active Inference"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-28719-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T18:12:01Z","timestamp":1679422321000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-28719-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031287183","9783031287190"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-28719-0_9","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Active Inference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwai-ws2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iwaiworkshop.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}