{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:26:57Z","timestamp":1765232817205,"version":"3.44.0"},"reference-count":92,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/cvpr.2019.00685","type":"proceedings-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T21:06:13Z","timestamp":1578603973000},"page":"6682-6692","source":"Crossref","is-referenced-by-count":44,"title":["Two Body Problem: Collaborative Visual Task Completion"],"prefix":"10.1109","author":[{"given":"Unnat","family":"Jain","sequence":"first","affiliation":[{"name":"UIUC"}]},{"given":"Luca","family":"Weihs","sequence":"additional","affiliation":[{"name":"Allen Institute for Artificial Intelligence"}]},{"given":"Eric","family":"Kolve","sequence":"additional","affiliation":[{"name":"Allen AI"}]},{"given":"Mohammad","family":"Rastegari","sequence":"additional","affiliation":[{"name":"Allen Institute for Artificial Intelligence"}]},{"given":"Svetlana","family":"Lazebnik","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[{"name":"Univ. of Washington, Allen Institute for Artificial Intelligence"}]},{"given":"Alexander G.","family":"Schwing","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"given":"Aniruddha","family":"Kembhavi","sequence":"additional","affiliation":[{"name":"Allen Institute for Artificial Intelligence"}]}],"member":"263","reference":[{"article-title":"MINOS: Multimodal indoor simulator for navigation in complex environments","year":"2017","author":"savva","key":"ref73"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.858856"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545495"},{"key":"ref70","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282485"},{"key":"ref77","article-title":"Estimating uncertain spatial relationships in robotics","author":"smith","year":"1986","journal-title":"Proc UAI"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref39","article-title":"Understanding grounded language learning agents","author":"hill","year":"2017","journal-title":"CoRR"},{"key":"ref75","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-011","article-title":"Statsmodels: Econometric and statistical modeling with python","author":"seabold","year":"2010","journal-title":"9th Python in Science Conference"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1998.677268"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref79","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Proc NIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"ref32","article-title":"Learning communication for multi-agent systems","author":"giles","year":"2002","journal-title":"Innovative Concepts for Agent-Based Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385934"},{"key":"ref30","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"CoRR"},{"article-title":"Unifying map and landmark based representations for visual navigation","year":"2017","author":"gupta","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"article-title":"Asynchronous Methods for Deep Reinforcement Learning","year":"2016","author":"mnih","key":"ref60"},{"key":"ref62","article-title":"Control of memory, active perception, and action in minecraft","author":"oh","year":"2016","journal-title":"Proc ICML"},{"key":"ref61","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11492","article-title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","author":"mordatch","year":"2018","journal-title":"Proc AAAI"},{"key":"ref63","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"CoRR"},{"key":"ref28","article-title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","author":"foerster","year":"2016","journal-title":"Proc NIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1995.525695"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/2.30720"},{"key":"ref65","article-title":"Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems","author":"panait","year":"2005","journal-title":"Proc AAMAS"},{"key":"ref66","article-title":"Fast, robust, continuous monocular egomotion computation","author":"phillips","year":"2016","journal-title":"Proc ICRA"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Coutnerfactual Multi-Agent Policy Gradients","author":"foerster","year":"2018","journal-title":"Proc AAAI"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500404"},{"key":"ref68","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1302458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"article-title":"Exploratory gradient boosting for reinforcement learning in complex domains","year":"2016","author":"abel","key":"ref1"},{"article-title":"Tarmac: Targeted multi-agent communication","year":"2018","author":"das","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref21","article-title":"Neural Modular Control for Embodied Question Answering","author":"das","year":"2018","journal-title":"Proc ECCV"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2000.854916"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238654"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344552"},{"article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","year":"2016","author":"duan","key":"ref25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(91)90014-C"},{"key":"ref51","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc ICML"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.60"},{"article-title":"Deep reinforcement learning with successor features for navigation across similar environments","year":"2016","author":"zhang","key":"ref90"},{"key":"ref59","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2017","journal-title":"Proc ICLR"},{"key":"ref58","article-title":"QueryPOMDP: POMDP-based communication in multiagent systems","author":"melo","year":"2011","journal-title":"in Multi-agent Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399095"},{"key":"ref56","article-title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","author":"lowe","year":"2017","journal-title":"Proc NIPS"},{"key":"ref55","article-title":"Learning physical intuition of block towers by example","author":"lerer","year":"2016","journal-title":"Proc ICML"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1250741"},{"article-title":"Multi-agent cooperation and the emergence of (natural) language","year":"2016","author":"lazaridou","key":"ref53"},{"key":"ref52","article-title":"Rapidly-exploring random trees: Progress and prospects","author":"lavalle","year":"2000","journal-title":"Algorithmic and Computational Robotics New Directions"},{"article-title":"HoME: a Household Multimodal Environment","year":"2017","author":"brodeur","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"journal-title":"The Complexity of Robot Motion Planning","year":"1988","author":"canny","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref15","article-title":"Gated-attention architectures for task-oriented language grounding","author":"chaplot","year":"2017","journal-title":"CoRR"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref17","article-title":"Learning transferable policies for monocular reactive mav control","author":"daftry","year":"2016","journal-title":"Proc ISER"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/BF00129684"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1092"},{"key":"ref83","article-title":"Extending q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Proc NIPS"},{"key":"ref19","article-title":"Embodied Question Answering","author":"das","year":"2018","journal-title":"Proc CVPR"},{"article-title":"Mazebase: A sandbox for learning from games","year":"2015","author":"sukhbaatar","key":"ref80"},{"article-title":"Torcs, the open racing car simulator","year":"2013","author":"wymann","key":"ref89"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2256686"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/21.44033"},{"article-title":"Playing doom with slam-augmented deep reinforcement learning","year":"2016","author":"bhatti","key":"ref5"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282312"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.329"},{"key":"ref86","article-title":"Learning a world model and planning with a self-organizing, dynamic neural system","author":"toussaint","year":"2003","journal-title":"Proc NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/70.88137"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910370376"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638021"},{"article-title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","year":"2018","author":"wu","key":"ref88"},{"key":"ref9","article-title":"A new approach to exploring language emergence as boundedly optimal control in the face of environmental and cognitive constraints","author":"bratman","year":"2010","journal-title":"Proc Int ’l Conv on Cognitive Modeling"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(02)00237-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"article-title":"AI2-THOR: An Interactive 3D Environment for Visual AI","year":"2017","author":"kolve","key":"ref48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008824626321"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989379"},{"key":"ref41","article-title":"The malmo platform for artificial intelligence experimentation","author":"johnson","year":"2016","journal-title":"Int Joint Conf AI"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SMCIA.2008.5045926"}],"event":{"name":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2019,6,15]]},"location":"Long Beach, CA, USA","end":{"date-parts":[[2019,6,20]]}},"container-title":["2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8938205\/8953184\/08953359.pdf?arnumber=8953359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:23:22Z","timestamp":1755800602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8953359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2019.00685","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}