{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:25:55Z","timestamp":1752981955785},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642284984"},{"type":"electronic","value":"9783642284991"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-28499-1_4","type":"book-chapter","created":{"date-parts":[[2012,2,27]],"date-time":"2012-02-27T08:59:11Z","timestamp":1330333151000},"page":"54-69","source":"Crossref","is-referenced-by-count":24,"title":["Multi-agent Reinforcement Learning for Simulating Pedestrian Navigation"],"prefix":"10.1007","author":[{"given":"Francisco","family":"Martinez-Gil","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miguel","family":"Lozano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando","family":"Fern\u00e1ndez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"4_CR1","unstructured":"Agre, P., Chapman, D.: Pengi: An implementation of a theory of activity. In: Proceedings of the Sixth National Conference on Artificial Intelligence, pp. 268\u2013272. Morgan Kaufmann (1987)"},{"issue":"1","key":"4_CR2","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.363440","volume":"6","author":"C. Chinrungrueng","year":"1995","unstructured":"Chinrungrueng, C., Sequin, C.: Optimal adaptive k-means algorithm with dynamic adjustment of learning rate. IEEE Transactions on Neural Networks\u00a06(1), 157\u2013169 (1995)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"4_CR3","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp. 746\u2013752. AAAI Press (1998)"},{"issue":"2","key":"4_CR4","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1002\/int.20255","volume":"23","author":"F. Fern\u00e1ndez","year":"2008","unstructured":"Fern\u00e1ndez, F., Borrajo, D.: Two steps reinforcement learning. International Journal of Intelligent Systems\u00a023(2), 213\u2013245 (2008)","journal-title":"International Journal of Intelligent Systems"},{"issue":"7","key":"4_CR5","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1016\/j.robot.2010.03.007","volume":"58","author":"F. Fern\u00e1ndez","year":"2010","unstructured":"Fern\u00e1ndez, F., Garc\u00eda, J., Veloso, M.: Probabilistic policy reuse for inter-task transfer learning. Robotics and Autonomous Systems\u00a058(7), 866\u2013871 (2010)","journal-title":"Robotics and Autonomous Systems"},{"key":"4_CR6","unstructured":"Garc\u00eda, J., L\u00f3pez-Bueno, I., Fern\u00e1ndez, F., Borrajo, D.: A Comparative Study of Discretization Approaches for State Space Generalization in the Keepaway Soccer Task. In: Reinforcement Learning: Algorithms, Implementations and Aplications. Nova Science Publishers (2010)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Hebing, D., Moln\u00e1r, P.: Social force model for pedestrian dynamics. Physics Review E, 4282\u20134286 (1995)","DOI":"10.1103\/PhysRevE.51.4282"},{"issue":"2","key":"4_CR8","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. Advances in Complex Systems\u00a010(2), 271\u2013288 (2007)","journal-title":"Advances in Complex Systems"},{"key":"4_CR9","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Int. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Int. Journal of Artificial Intelligence Research"},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"R.B.L. Busoniu","year":"2008","unstructured":"Busoniu, R.B.L., Schutter, B.D.: A comprehensive survey of multi-agent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics Part C: Applications and Reviews\u00a038, 156\u2013172 (2008)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics Part C: Applications and Reviews"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Mataric, M.J.: Learning to behave socially. In: From Animals to Animats: International Conference on Simulation of Adaptive Behavior, pp. 453\u2013462. MIT Press (1994)","DOI":"10.7551\/mitpress\/3117.003.0065"},{"key":"4_CR12","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-540-47064-9_29","volume-title":"Pedestrian and Evacuation Dynamics 2005","author":"A. Nakayama","year":"2007","unstructured":"Nakayama, A., Sugiyama, Y., Hasebe, K.: Instability of pedestrian flow and phase structure in a two\u2013dimensional optimal velocity model. In: Pedestrian and Evacuation Dynamics 2005, pp. 321\u2013332. Springer, Heidelberg (2007)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Schadschneider, A., Klingsch, W., Kl\u00fcpfel, H., Kretz, T., Rogsch, C., Seyfried, A.: Evacuation dynamics: Empirical results, modeling and applications. In: Encyclopedia of Complexity and Systems Science, pp. 3142\u20133176 (2009)","DOI":"10.1007\/978-0-387-30440-3_187"},{"key":"4_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1007\/3-540-60923-7_30","volume-title":"Adaption and Learning in Multi-Agent Systems","author":"S. Sen","year":"1996","unstructured":"Sen, S., Sekaran, M.: Multiagent Coordination with Learning Classifier Systems. In: Weiss, G., Sen, S. (eds.) IJCAI-WS 1995. LNCS, vol.\u00a01042, pp. 218\u2013233. Springer, Heidelberg (1996)"},{"issue":"3","key":"4_CR15","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1287\/trsc.1090.0263","volume":"43","author":"A. Seyfried","year":"2009","unstructured":"Seyfried, A., Passon, O., Steffen, B., Boltes, M., Rupprecht, T., Klingsch, W.: New insights into pedestrian flow through bottlenecks. Transportation Science\u00a043(3), 395\u2013406 (2009)","journal-title":"Transportation Science"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. In: Machine Learning, pp. 9\u201344. Kluwer Academic Publishers (1988)","DOI":"10.1007\/BF00115009"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Taylor, M.E., Stone, P.: Behavior transfer for value-function-based reinforcement learning. In: The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems (July 2005)","DOI":"10.1145\/1082473.1082482"},{"key":"4_CR18","volume-title":"Proceedings of the Sixth AAAI Conference On Artificial Intelligence and Interactive Digital Entertainment","author":"L. Torrey","year":"2010","unstructured":"Torrey, L.: Crowd simulation via multi-agent reinforcement learning. In: Proceedings of the Sixth AAAI Conference On Artificial Intelligence and Interactive Digital Entertainment. AAAI Press, Menlo Park (2010)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Whitehead, S.D., Ballard, D.H.: Learning to perceive and act by trial and error. Machine Learning, 45\u201383 (1991)","DOI":"10.1007\/BF00058926"}],"container-title":["Lecture Notes in Computer Science","Adaptive and Learning Agents"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-28499-1_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T19:01:42Z","timestamp":1713639702000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-28499-1_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642284984","9783642284991"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-28499-1_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}