{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T15:00:54Z","timestamp":1773241254947,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8463211","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:28:03Z","timestamp":1537554483000},"page":"7533-7540","source":"Crossref","is-referenced-by-count":28,"title":["Intent-Aware Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Qi","sequence":"first","affiliation":[]},{"given":"Song-Chun","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"You only look once: Unified, real-time object detection","author":"redmon","year":"2016","journal-title":"CVPR"},{"key":"ref38","article-title":"Ros: an open-source robot operating system","author":"quigley","year":"2009","journal-title":"ICRA Workshop on Open Source Software"},{"key":"ref33","author":"camerer","year":"2003","journal-title":"Behavioral Game Theory Experiments in Strategic Interaction"},{"key":"ref32","author":"weibull","year":"1997","journal-title":"Evolutionary Game Theory"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/science.1107621"},{"key":"ref30","article-title":"Three-month-old infants attribute goals to a non-human agent","author":"luo","year":"0","journal-title":"Developmental Science"},{"key":"ref37","article-title":"V-rep: a versatile and scalable robot simulation framework","author":"rohmer","year":"2013","journal-title":"IROS"},{"key":"ref36","article-title":"Speech discrimination by dynamic programming","author":"vintsyuk","year":"1968","journal-title":"Cybernetics"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114727"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref10","article-title":"Intention-aware online pomdp planning for autonomous driving in a crowd","author":"bai","year":"2015","journal-title":"ICRA IEEE"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205651"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-36279-8_29","article-title":"Intention-aware motion planning","author":"bandyopadhyay","year":"2013","journal-title":"Algorithmic Foundations of Robotics X"},{"key":"ref12","article-title":"Feeling the force: Integrating force and pose for fluent discovery through imitation learning to open medicine bottles","author":"edmonds","year":"2017","journal-title":"IROS"},{"key":"ref13","article-title":"A game-theoretic approach for adaptive action selection in close proximity human-robot-collaboration","author":"gabler","year":"2017","journal-title":"ICRA IEEE"},{"key":"ref14","article-title":"Human-robot collaborative manipulation planning using early prediction of human motion","author":"mainprice","year":"2013","journal-title":"IROS IEEE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref16","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"AAAI"},{"key":"ref17","article-title":"Reinforcement learning of coordination in cooperative multi-agent systems","volume":"2002","author":"kapetanakis","year":"2002","journal-title":"AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref19","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-0277(98)00058-4"},{"key":"ref4","article-title":"Inferring human intent from video by sampling hierarchical plans","author":"holtzen","year":"2016","journal-title":"IROS IEEE"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1145\/860575.860689","article-title":"Coordination in multiagent reinforcement learning: A bayesian approach","author":"chalkiadakis","year":"2003","journal-title":"Proceedings of the second international joint conference on Autonomous agents and multiagent systems"},{"key":"ref3","article-title":"Activity forecasting","author":"kitani","year":"2012","journal-title":"ECCV"},{"key":"ref6","article-title":"Learning and inferring” dark matter” and predicting human intents and trajectories in videos","author":"xie","year":"2017","journal-title":"PAMI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogdev.2010.09.001"},{"key":"ref5","article-title":"Intent-aware longterm prediction of pedestrian motion","author":"karasev","year":"2016","journal-title":"ICRA IEEE"},{"key":"ref8","article-title":"Modeling cooperative navigation in dense human crowds","author":"vemula","year":"2017","journal-title":"ICRA"},{"key":"ref7","article-title":"Predicting human activities using stochastic grammar","author":"qi","year":"2017","journal-title":"ICCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-398532-3.00007-5"},{"key":"ref9","article-title":"Coun-terfactual reasoning about intent for interactive navigation in dynamic environments","author":"bordallo","year":"2015","journal-title":"IROS IEEE"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.07.005"},{"key":"ref20","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","author":"hu","year":"1998","journal-title":"ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref42","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"tan","year":"1993","journal-title":"ICML"},{"key":"ref24","article-title":"Deep decentralized multi-task multi-agent rl under partial observability","author":"omidshafiei","year":"2017","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368178"},{"key":"ref23","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NIPS"},{"key":"ref26","author":"gmytrasiewicz","year":"2005","journal-title":"A framework for sequential planning in multi-agent settings"},{"key":"ref25","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"ICML"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08463211.pdf?arnumber=8463211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:28:50Z","timestamp":1598210930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8463211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8463211","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}