{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:37:35Z","timestamp":1729676255134,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414712","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"3490-3494","source":"Crossref","is-referenced-by-count":0,"title":["Self-Inference Of Others\u2019 Policies For Homogeneous Agents In Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qifeng","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2024997"},{"key":"ref11","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"h\u00fcttenrauch","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref14","first-page":"31","article-title":"Agent modeling as auxiliary task for deep reinforcement learning","author":"hernandez-leal","year":"2019","journal-title":"AAAI Artificial Intelligence and Interactive Digital Entertainment"},{"key":"ref15","first-page":"1108","article-title":"Modelling the dynamic joint policy of team-mates with attention multi-agent ddpg","author":"mao","year":"2019","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref16","first-page":"4254","article-title":"Modeling others using oneself in multi-agent reinforcement learning","author":"raileanu","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref17"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref3","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref5","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":"ref8","first-page":"1388","article-title":"A deep policy inference q-network for multi-agent systems","author":"hong","year":"2018","journal-title":"International Conference on Autonomous Agents and Multi-Agent Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/860575.860689"},{"article-title":"Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games","year":"2017","author":"peng","key":"ref2"},{"key":"ref1","article-title":"Coordinated multi-robot exploration under communication constraints using decentralized markov decision processes","author":"matignon","year":"2012","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-44927-7_17"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414712.pdf?arnumber=9414712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T03:31:58Z","timestamp":1672111918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414712","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}