{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T20:57:33Z","timestamp":1729630653728,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,8]],"date-time":"2021-08-08T00:00:00Z","timestamp":1628380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,8]],"date-time":"2021-08-08T00:00:00Z","timestamp":1628380800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,8]],"date-time":"2021-08-08T00:00:00Z","timestamp":1628380800000},"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":[[2021,8,8]]},"DOI":"10.1109\/ro-man50785.2021.9515411","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T22:07:53Z","timestamp":1629756473000},"page":"649-656","source":"Crossref","is-referenced-by-count":0,"title":["Competitive physical interaction by reinforcement learning agents using intention estimation"],"prefix":"10.1109","author":[{"given":"Hiroki","family":"Noda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Nishikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryuma","family":"Niiyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuo","family":"Kuniyoshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref31"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10916","article-title":"The option-critic architecture","volume":"31","author":"bacon","year":"2017","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3049539"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"berner","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","year":"2017","author":"lowe","key":"ref15"},{"key":"ref16","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"International Conference on Machine Learning"},{"article-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"article-title":"Emergent complexity via multi-agent competition","year":"2017","author":"bansal","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2012.36"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206624"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1089\/neu.2010.1501"},{"article-title":"Emergent tool use from multi-agent autocurricula","year":"2019","author":"baker","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2671428"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2132\/personality.27.3.7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0055773"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2015.7419040"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2015.p0543"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"article-title":"Variational autoencoders for opponent modeling in multi-agent systems","year":"2020","author":"papoudakis","key":"ref22"},{"article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","year":"2019","author":"papoudakis","key":"ref21"},{"key":"ref24","first-page":"1802","article-title":"Learning policy representations in multiagent systems","author":"grover","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"kingma","key":"ref23"},{"key":"ref26","article-title":"Learning against non-stationary agents with opponent modelling and deep reinforcement learning","author":"everett","year":"2018","journal-title":"The 2018 AAAI Spring Symposium Series"},{"key":"ref25","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","author":"raileanu","year":"2018","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2021,8,8]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2021,8,12]]}},"container-title":["2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9515344\/9515312\/09515411.pdf?arnumber=9515411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T22:34:50Z","timestamp":1673130890000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9515411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,8]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ro-man50785.2021.9515411","relation":{},"subject":[],"published":{"date-parts":[[2021,8,8]]}}}