{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:15:50Z","timestamp":1777655750569,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T00:00:00Z","timestamp":1602806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Ontario Research Fund","award":["Intelligent Systems for Sustainable Urban Mobility (ISSUM)"],"award-info":[{"award-number":["Intelligent Systems for Sustainable Urban Mobility (ISSUM)"]}]},{"name":"NSERC","award":["CreateDAV"],"award-info":[{"award-number":["CreateDAV"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,16]]},"DOI":"10.1145\/3424636.3426894","type":"proceedings-article","created":{"date-parts":[[2020,11,22]],"date-time":"2020-11-22T20:43:50Z","timestamp":1606077830000},"page":"1-10","source":"Crossref","is-referenced-by-count":20,"title":["Deep Integration of Physical Humanoid Control and Crowd Navigation"],"prefix":"10.1145","author":[{"given":"Brandon","family":"Haworth","sequence":"first","affiliation":[{"name":"University of Victoria Victoria, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Glen","family":"Berseth","sequence":"additional","affiliation":[{"name":"University of California Berkeley Berkeley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seonghyeon","family":"Moon","sequence":"additional","affiliation":[{"name":"Rutgers University New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petros","family":"Faloutsos","sequence":"additional","affiliation":[{"name":"York University Toronto Canada and University Health Network: Toronto Rehabilitation Institute, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mubbasir","family":"Kapadia","sequence":"additional","affiliation":[{"name":"Rutgers University New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,11,22]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1732643.1732776"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10347-6_20"},{"key":"e_1_3_2_2_3_1","unstructured":"Glen Berseth Mubbasir Kapadia and Petros Faloutsos. 2015. Robust space-time footsteps for agent-based steering. Computer Animation and Virtual Worlds(2015).  Glen Berseth Mubbasir Kapadia and Petros Faloutsos. 2015. Robust space-time footsteps for agent-based steering. Computer Animation and Virtual Worlds(2015)."},{"key":"e_1_3_2_2_4_1","unstructured":"Glen Berseth Xue\u00a0Bin Peng and Michiel van\u00a0de Panne. 2018. Terrain RL Simulator. CoRR abs\/1804.06424(2018). arxiv:1804.06424http:\/\/arxiv.org\/abs\/1804.06424  Glen Berseth Xue\u00a0Bin Peng and Michiel van\u00a0de Panne. 2018. Terrain RL Simulator. CoRR abs\/1804.06424(2018). arxiv:1804.06424http:\/\/arxiv.org\/abs\/1804.06424"},{"key":"e_1_3_2_2_5_1","volume-title":"Optic flow drives human visuo-locomotor adaptation. Current biology 17, 23","author":"Bruggeman Hugo","year":"2007"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/295240.295800"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1642194.1642205"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383287"},{"key":"e_1_3_2_2_10_1","unstructured":"Scott Fujimoto Herke Van\u00a0Hoof and David Meger. 2018. Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477(2018).  Scott Fujimoto Herke Van\u00a0Hoof and David Meger. 2018. Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477(2018)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976606776241057"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3306127.3331992"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/35035023"},{"key":"e_1_3_2_2_15_1","volume-title":"Social force model for pedestrian dynamics. Physical review E 51, 5","author":"Helbing Dirk","year":"1995"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"e_1_3_2_2_17_1","volume-title":"International Joint Conference on Artificial Intelligence (IJCAI), Vol.\u00a0vol.2. 1094 \u2013 8.","author":"Kaelbling L\u00a0P","year":"1993"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2911068"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2019406.2019414"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10347-6_4"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-014-0946-1"},{"key":"e_1_3_2_2_22_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014).","author":"Kingma P","year":"2014"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1996.503784"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274247.3274510"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091574.3091594"},{"key":"e_1_3_2_2_26_1","unstructured":"Ryan Lowe YI WU Aviv Tamar Jean Harb OpenAI Pieter\u00a0Abbeel and Igor Mordatch. 2017. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. In Advances in Neural Information Processing Systems 30. 6379\u20136390.  Ryan Lowe YI WU Aviv Tamar Jean Harb OpenAI Pieter\u00a0Abbeel and Igor Mordatch. 2017. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. In Advances in Neural Information Processing Systems 30. 6379\u20136390."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-014-9252-6"},{"key":"e_1_3_2_2_28_1","unstructured":"Josh Merel Arun Ahuja Vu Pham Saran Tunyasuvunakool Siqi Liu Dhruva Tirumala Nicolas Heess and Greg Wayne. 2018. Hierarchical visuomotor control of humanoids. CoRR abs\/1811.09656(2018). arxiv:1811.09656http:\/\/arxiv.org\/abs\/1811.09656  Josh Merel Arun Ahuja Vu Pham Saran Tunyasuvunakool Siqi Liu Dhruva Tirumala Nicolas Heess and Greg Wayne. 2018. Hierarchical visuomotor control of humanoids. CoRR abs\/1811.09656(2018). arxiv:1811.09656http:\/\/arxiv.org\/abs\/1811.09656"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/37.257893"},{"key":"e_1_3_2_2_30_1","volume-title":"Human-level control through deep reinforcement learning. Nature 518, 7540","author":"Mnih Volodymyr","year":"2015"},{"key":"e_1_3_2_2_31_1","unstructured":"Ranjit Nair Milind Tambe Makoto Yokoo David Pynadath and Stacy Marsella. 2003. Taming decentralized POMDPs: Towards efficient policy computation for multiagent settings. In IJCAI Vol.\u00a03. 705\u2013711.  Ranjit Nair Milind Tambe Makoto Yokoo David Pynadath and Stacy Marsella. 2003. Taming decentralized POMDPs: Towards efficient policy computation for multiagent settings. In IJCAI Vol.\u00a03. 705\u2013711."},{"key":"e_1_3_2_2_32_1","unstructured":"OpenAI. 2018. OpenAI Five. https:\/\/blog.openai.com\/openai-five\/.  OpenAI. 2018. OpenAI Five. https:\/\/blog.openai.com\/openai-five\/."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3099844"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045319"},{"key":"e_1_3_2_2_36_1","volume-title":"International Conference on Learning Representations (ICLR","author":"Schulman John","year":"2016"},{"key":"e_1_3_2_2_37_1","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal Policy Optimization Algorithms. ArXiv e-prints (July 2017). arxiv:1707.06347\u00a0[cs.LG]  J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal Policy Optimization Algorithms. ArXiv e-prints (July 2017). arxiv:1707.06347\u00a0[cs.LG]"},{"key":"e_1_3_2_2_38_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017).  John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3044850"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/cav.403"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00198086"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091529.3091572"},{"key":"e_1_3_2_2_44_1","unstructured":"Hongyao Tang Jianye Hao Tangjie Lv Yingfeng Chen Zongzhang Zhang Hangtian Jia Chunxu Ren Yan Zheng Changjie Fan and Li Wang. 2018. Hierarchical deep multiagent reinforcement learning. arXiv preprint arXiv:1809.09332(2018).  Hongyao Tang Jianye Hao Tangjie Lv Yingfeng Chen Zongzhang Zhang Hangtian Jia Chunxu Ren Yan Zheng Changjie Fan and Li Wang. 2018. Hierarchical deep multiagent reinforcement learning. arXiv preprint arXiv:1809.09332(2018)."},{"key":"e_1_3_2_2_45_1","unstructured":"Daniel Thalmann and Soraia\u00a0Raupp Musse. 2013. . Springer.  Daniel Thalmann and Soraia\u00a0Raupp Musse. 2013. . Springer."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/3014666.3014683"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1186\/1743-0003-12-1"},{"key":"e_1_3_2_2_48_1","volume-title":"Robotics research","author":"Den\u00a0Berg Jur Van"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"e_1_3_2_2_50_1","volume-title":"Optic flow is used to control human walking. Nature neuroscience 4, 2","author":"Warren\u00a0Jr H","year":"2001"},{"key":"e_1_3_2_2_51_1","unstructured":"Manuel Watter Jost Springenberg Joschka Boedecker and Martin Riedmiller. 2015. Embed to control: A locally linear latent dynamics model for control from raw images. In Advances in neural information processing systems. 2746\u20132754.  Manuel Watter Jost Springenberg Joschka Boedecker and Martin Riedmiller. 2015. Embed to control: A locally linear latent dynamics model for control from raw images. In Advances in neural information processing systems. 2746\u20132754."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/1732643.1732952"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276509"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140083"},{"key":"e_1_3_2_2_55_1","unstructured":"Amy Zhang Nicolas Ballas and Joelle Pineau. 2018. A dissection of overfitting and generalization in continuous reinforcement learning. arXiv preprint arXiv:1806.07937(2018).  Amy Zhang Nicolas Ballas and Joelle Pineau. 2018. A dissection of overfitting and generalization in continuous reinforcement learning. arXiv preprint arXiv:1806.07937(2018)."}],"event":{"name":"MIG '20: Motion, Interaction and Games","location":"Virtual Event SC USA","acronym":"MIG '20","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Motion, Interaction and Games"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3424636.3426894","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3424636.3426894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:26Z","timestamp":1750197746000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3424636.3426894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,16]]},"references-count":55,"alternative-id":["10.1145\/3424636.3426894","10.1145\/3424636"],"URL":"https:\/\/doi.org\/10.1145\/3424636.3426894","relation":{},"subject":[],"published":{"date-parts":[[2020,10,16]]}}}