{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:20:01Z","timestamp":1742995201520,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030209360"},{"type":"electronic","value":"9783030209377"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20937-7_6","type":"book-chapter","created":{"date-parts":[[2019,5,18]],"date-time":"2019-05-18T20:07:12Z","timestamp":1558210032000},"page":"81-95","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Inverse Reinforcement Learning for Agents Behavior in a Crowd Simulator"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1717-2506","authenticated-orcid":false,"given":"Nahum","family":"Alvarez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1987-5336","authenticated-orcid":false,"given":"Itsuki","family":"Noda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,19]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 1. ACM (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"6_CR2","unstructured":"Alger, M.: Deep inverse reinforcement learning (2015)"},{"key":"6_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/978-3-319-46882-2_9","volume-title":"Autonomous Agents and Multiagent Systems","author":"L Crociani","year":"2016","unstructured":"Crociani, L., L\u00e4mmel, G., Vizzari, G.: Multi-scale simulation for crowd management: a case study in an urban scenario. In: Osman, N., Sierra, C. (eds.) AAMAS 2016. LNCS (LNAI), vol. 10002, pp. 147\u2013162. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46882-2_9"},{"issue":"2","key":"6_CR4","first-page":"163","volume":"10","author":"L Crociani","year":"2016","unstructured":"Crociani, L., Vizzari, G., Yanagisawa, D., Nishinari, K., Bandini, S.: Route choice in pedestrian simulation: design and evaluation of a model based on empirical observations. Intell. Artif. 10(2), 163\u2013182 (2016)","journal-title":"Intell. Artif."},{"key":"6_CR5","unstructured":"Dvijotham, K., Todorov, E.: Inverse optimal control with linearly-solvable MDPs. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 335\u2013342 (2010)"},{"key":"6_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-3-319-64798-2_12","volume-title":"Multiagent System Technologies","author":"J Faccin","year":"2017","unstructured":"Faccin, J., Nunes, I., Bazzan, A.: Understanding the behaviour of learning-based BDI agents in the Braess\u2019 paradox. In: Berndt, J.O., Petta, P., Unland, R. (eds.) MATES 2017. LNCS (LNAI), vol. 10413, pp. 187\u2013204. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64798-2_12"},{"issue":"5","key":"6_CR7","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","volume":"51","author":"D Helbing","year":"1995","unstructured":"Helbing, D., Molnar, P.: Social force model for pedestrian dynamics. Phys. Rev. E 51(5), 4282\u20134286 (1995)","journal-title":"Phys. Rev. E"},{"key":"6_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-50127-7_45","volume-title":"AI 2016: Advances in Artificial Intelligence","author":"M Herman","year":"2016","unstructured":"Herman, M., Gindele, T., Wagner, J., Schmitt, F., Quignon, C., Burgard, W.: Learning high-level navigation strategies via inverse reinforcement learning: a comparative analysis. In: Kang, B.H., Bai, Q. (eds.) AI 2016. LNCS (LNAI), vol. 9992, pp. 525\u2013534. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-50127-7_45"},{"issue":"2","key":"6_CR9","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1142\/S0219525907001355","volume":"10","author":"A Johansson","year":"2007","unstructured":"Johansson, A., Helbing, D., Shukla, P.K.: Specification of the social force pedestrian model by evolutionary adjustment to video tracking data. Adv. Complex Syst. 10(2), 271\u2013288 (2007). https:\/\/doi.org\/10.1142\/S0219525907001355","journal-title":"Adv. Complex Syst."},{"key":"6_CR10","unstructured":"Kohjima, M., Matsubayashi, T., Sawada, H.: What-if prediction via inverse reinforcement learning. In: Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2017, Marco Island, Florida, USA, 22\u201324 May 2017, pp. 74\u201379 (2017). https:\/\/aaai.org\/ocs\/index.php\/FLAIRS\/FLAIRS17\/paper\/view\/15503"},{"key":"6_CR11","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1007\/978-3-319-02447-9_105","volume-title":"Pedestrian and Evacuation Dynamics 2012","author":"G L\u00e4mmel","year":"2014","unstructured":"L\u00e4mmel, G., Plaue, M.: Getting out of the way: collision-avoiding pedestrian models compared to the RealWorld. In: Weidmann, U., Kirsch, U., Schreckenberg, M. (eds.) Pedestrian and Evacuation Dynamics 2012, pp. 1275\u20131289. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-02447-9_105"},{"issue":"1","key":"6_CR12","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.trc.2009.04.020","volume":"18","author":"G L\u00e4mmel","year":"2010","unstructured":"L\u00e4mmel, G., Grether, D., Nagel, K.: The representation and implementation of time-dependent inundation in large-scale microscopic evacuation simulations. Transp. Res. Part C Emerg. Technol. 18(1), 84\u201398 (2010)","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"6_CR13","unstructured":"Levine, S., Popovic, Z., Koltun, V.: Nonlinear inverse reinforcement learning with Gaussian processes. In: Advances in Neural Information Processing Systems, pp. 19\u201327 (2011)"},{"issue":"3\u20134","key":"6_CR14","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1002\/cav.238","volume":"19","author":"L Luo","year":"2008","unstructured":"Luo, L., et al.: Agent-based human behavior modeling for crowd simulation. Comput. Animat. Virtual Worlds 19(3\u20134), 271\u2013281 (2008)","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"6_CR15","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.simpat.2017.03.003","volume":"74","author":"F Martinez-Gil","year":"2017","unstructured":"Martinez-Gil, F., Lozano, M., Fern\u00e1ndez, F.: Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models. Simul. Model. Pract. Theory 74, 117\u2013133 (2017)","journal-title":"Simul. Model. Pract. Theory"},{"key":"6_CR16","unstructured":"Ng, A.Y., Russell, S.J., et al.: Algorithms for inverse reinforcement learning. In: ICML, pp. 663\u2013670 (2000)"},{"key":"6_CR17","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/978-1-4419-7695-6_29","volume-title":"Extreme Environmental Events","author":"A Schadschneider","year":"2011","unstructured":"Schadschneider, A., Klingsch, W., Kl\u00fcpfel, H., Kretz, T., Rogsch, C., Seyfried, A.: Evacuation dynamics: empirical results, modeling and applications. In: Meyers, R. (ed.) Extreme Environmental Events, pp. 517\u2013550. Springer, New York (2011). https:\/\/doi.org\/10.1007\/978-1-4419-7695-6_29"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"de Albuquerque Siebra, C., Botelho Neto, G.P.: Evolving the behavior of autonomous agents in strategic combat scenarios via sarsa reinforcement learning. In: Proceedings of the 2014 Brazilian Symposium on Computer Games and Digital Entertainment, SBGAMES 2014, Washington, DC, USA, pp. 115\u2013122. IEEE Computer Society (2014). https:\/\/doi.org\/10.1109\/SBGAMES.2014.36","DOI":"10.1109\/SBGAMES.2014.36"},{"key":"6_CR19","unstructured":"\u0160o\u0161i\u0107, A., KhudaBukhsh, W.R., Zoubir, A.M., Koeppl, H.: Inverse reinforcement learning in swarm systems. In: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems, pp. 1413\u20131421. International Foundation for Autonomous Agents and Multiagent Systems (2017)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Svetlik, M., Leonetti, M., Sinapov, J., Shah, R., Walker, N., Stone, P.: Automatic curriculum graph generation for reinforcement learning agents, November 2016. http:\/\/eprints.whiterose.ac.uk\/108931\/","DOI":"10.1609\/aaai.v31i1.10933"},{"issue":"1","key":"6_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.compenvurbsys.2011.07.005","volume":"36","author":"PM Torrens","year":"2012","unstructured":"Torrens, P.M., Nara, A., Li, X., Zhu, H., Griffin, W.A., Brown, S.B.: An extensible simulation environment and movement metrics for testing walking behavior in agent-based models. Comput. Environ. Urban Syst. 36(1), 1\u201317 (2012)","journal-title":"Comput. Environ. Urban Syst."},{"key":"6_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-642-11161-7_52","volume-title":"Principles of Practice in Multi-Agent Systems","author":"T Yamashita","year":"2009","unstructured":"Yamashita, T., Soeda, S., Noda, I.: Evacuation planning assist system with network model-based pedestrian simulator. In: Yang, J.-J., Yokoo, M., Ito, T., Jin, Z., Scerri, P. (eds.) PRIMA 2009. LNCS (LNAI), vol. 5925, pp. 649\u2013656. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-11161-7_52"},{"issue":"6","key":"6_CR23","doi-asserted-by":"publisher","first-page":"68005","DOI":"10.1209\/0295-5075\/93\/68005","volume":"93","author":"F Zanlungo","year":"2011","unstructured":"Zanlungo, F., Ikeda, T., Kanda, T.: Social force model with explicit collision prediction. EPL (Europhys. Lett.) 93(6), 68005 (2011)","journal-title":"EPL (Europhys. Lett.)"},{"issue":"5","key":"6_CR24","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1007\/s10458-016-9334-8","volume":"30","author":"J Zhong","year":"2016","unstructured":"Zhong, J., Cai, W., Luo, L., Zhao, M.: Learning behavior patterns from video for agent-based crowd modeling and simulation. Auton. Agents Multi-Agent Syst. 30(5), 990\u20131019 (2016)","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"6_CR25","unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., Dey, A.K.: Maximum entropy inverse reinforcement learning. In: AAAI, Chicago, IL, USA, vol. 8, pp. 1433\u20131438 (2008)"}],"container-title":["Lecture Notes in Computer Science","Massively Multi-Agent Systems II"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20937-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T07:37:36Z","timestamp":1663486656000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20937-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030209360","9783030209377"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20937-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"19 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Massively Multiagent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Stockholm","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmas2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ai.soc.i.kyoto-u.ac.jp\/mmas2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}