{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:35:19Z","timestamp":1730255719774,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196810","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"11338-11344","source":"Crossref","is-referenced-by-count":4,"title":["Collision-free Navigation of Human-centered Robots via Markov Games"],"prefix":"10.1109","author":[{"given":"Guo","family":"Ye","sequence":"first","affiliation":[]},{"given":"Qinjie","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Tzung-Han","family":"Juang","sequence":"additional","affiliation":[]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref38","article-title":"Adversarial policies: Attacking deep reinforcement learning","author":"gleave","year":"2019","journal-title":"arXiv preprint arXiv 1905 10520"},{"key":"ref33","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915576234"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2120810"},{"key":"ref37","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2017","journal-title":"arXiv preprint arXiv 1710 03748"},{"key":"ref36","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"arXiv preprint arXiv 1802 08908"},{"key":"ref34","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Long-range indoor navigation with prm-rl","author":"francis","year":"2019","journal-title":"arXiv preprint arXiv 1902 05023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-008-0014-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942731"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139511"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"},{"key":"ref19","article-title":"Friend-or-foe q-learning in general-sum games","author":"littman","year":"2001","journal-title":"Int Conference on Artificial Intelligence (AAAI)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-0427(00)00433-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref27","article-title":"Modeling others using oneself in multi-agent reinforcement learning","author":"raileanu","year":"2018","journal-title":"arXiv preprint arXiv 1802 09085"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/21.44033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref29","first-page":"188","article-title":"Parametric simplex method for sparse learning","author":"pang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/100.580977","article-title":"The dynamic window approach to collision avoidance","volume":"4","author":"fox","year":"1997","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"ref8","article-title":"A data-efficient framework for training and sim-to-real transfer of navigation policies","author":"bharadhwaj","year":"2018","journal-title":"arXiv preprint arXiv 1810 06008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2010.2076851"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793810"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1682\/JRRD.2005.02.0046"},{"key":"ref20","first-page":"1603","article-title":"Reinforcement learning to play an optimal nash equilibrium in team markov games","author":"wang","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Deep q-learning for nash equilibria: Nash-dqn","author":"casgrain","year":"2019","journal-title":"arXiv preprint arXiv 1904 12848"},{"key":"ref21","first-page":"1039","article-title":"Nash q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","article-title":"A comprehensive survey of multiagent reinforcement learning","volume":"38","author":"bu","year":"2008","journal-title":"IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"article-title":"Automatic differentiation in pytorch","year":"2017","author":"paszke","key":"ref44"},{"key":"ref26","first-page":"506","article-title":"Best-response multiagent learning in non-stationary environments","author":"weinberg","year":"2004","journal-title":"Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems-Volume 2"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-19457-3_1","article-title":"Reciprocal n-body collision avoidance","author":"van den berg","year":"2011","journal-title":"Robotics Research"},{"key":"ref25","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"hernandez-leal","year":"2017","journal-title":"arXiv preprint arXiv 1707 09562"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196810.pdf?arnumber=9196810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:18:44Z","timestamp":1656375524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196810","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}