{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T11:08:13Z","timestamp":1756897693223,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,11,5]],"date-time":"2018-11-05T00:00:00Z","timestamp":1541376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Swedish e-Science Research Centre (SeRC)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,11,5]]},"DOI":"10.1145\/3267851.3267914","type":"proceedings-article","created":{"date-parts":[[2018,11,21]],"date-time":"2018-11-21T14:02:20Z","timestamp":1542808940000},"page":"307-312","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Pedestrian simulation as multi-objective reinforcement learning"],"prefix":"10.1145","author":[{"given":"Naresh Balaji","family":"Ravichandran","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"given":"Fangkai","family":"Yang","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"given":"Christopher","family":"Peters","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"given":"Anders","family":"Lansner","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"given":"Pawel","family":"Herman","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}]}],"member":"320","published-online":{"date-parts":[[2018,11,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3141\/1644-04"},{"volume-title":"Proc. Artificial Life VII. 437--445","year":"2000","author":"Blue Victor","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.17815\/CD.2016.1"},{"volume-title":"ALAN: Adaptive Learning for Multi-Agent Navigation. arXiv preprint arXiv:1710.04296","year":"2017","author":"Godoy Julio","key":"e_1_3_2_1_4_1"},{"volume-title":"Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems, 1577--1585","year":"2015","author":"Godoy Julio E","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Dirk Helbing and Peter Molnar. 1995. Social force model for pedestrian dynamics. Physical review E 51 5 (1995) 4282.  Dirk Helbing and Peter Molnar. 1995. Social force model for pedestrian dynamics. Physical review E 51 5 (1995) 4282.","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0191-2615(01)00015-7"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Roger L Hughes. 2003. The flow of human crowds. Annual review of fluid mechanics 35 1 (2003) 169--182.  Roger L Hughes. 2003. The flow of human crowds. Annual review of fluid mechanics 35 1 (2003) 169--182.","DOI":"10.1146\/annurev.fluid.35.101101.161136"},{"volume-title":"17th UKSIMAMSS International Conference on Modelling and Simulation. 111--116","year":"2015","author":"Ijaz Kiran","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10347-6_4"},{"key":"e_1_3_2_1_11_1","unstructured":"Vijay R Konda and John N Tsitsiklis. 2000. Actor-critic algorithms. In Advances in neural information processing systems. 1008--1014.   Vijay R Konda and John N Tsitsiklis. 2000. Actor-critic algorithms. In Advances in neural information processing systems. 1008--1014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-014-9252-6"},{"key":"e_1_3_2_1_13_1","unstructured":"Richard S Sutton and Andrew G Barto. 1998. Reinforcement learning: An introduction. Vol. 1. MIT press Cambridge.   Richard S Sutton and Andrew G Barto. 1998. Reinforcement learning: An introduction. Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Lisa Torrey. 2010. Crowd Simulation Via Multi-Agent Reinforcement Learning.. In AIIDE.   Lisa Torrey. 2010. Crowd Simulation Via Multi-Agent Reinforcement Learning.. In AIIDE.","DOI":"10.1609\/aiide.v6i1.12390"},{"volume-title":"Robotics research","author":"Den Berg Jur Van","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.72.026112"}],"event":{"name":"IVA '18: International Conference on Intelligent Virtual Agents","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"],"location":"Sydney NSW Australia","acronym":"IVA '18"},"container-title":["Proceedings of the 18th International Conference on Intelligent Virtual Agents"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3267851.3267914","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3267851.3267914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:43:59Z","timestamp":1750207439000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3267851.3267914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,5]]},"references-count":17,"alternative-id":["10.1145\/3267851.3267914","10.1145\/3267851"],"URL":"https:\/\/doi.org\/10.1145\/3267851.3267914","relation":{},"subject":[],"published":{"date-parts":[[2018,11,5]]},"assertion":[{"value":"2018-11-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}