{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:18:28Z","timestamp":1740100708482,"version":"3.37.3"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T00:00:00Z","timestamp":1651190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T00:00:00Z","timestamp":1651190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000348","name":"Calouste Gulbenkian Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000348","name":"Calouste Gulbenkian Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,29]]},"DOI":"10.1109\/icarsc55462.2022.9784785","type":"proceedings-article","created":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T19:49:41Z","timestamp":1654112981000},"page":"130-135","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning for Multi-Agent Competitive Scenarios"],"prefix":"10.1109","author":[{"given":"Manuel","family":"Coutinho","sequence":"first","affiliation":[{"name":"FEUP - Faculty of Engineering of the University of Porto University of Porto,Porto,Portugal"}]},{"given":"Luis Paulo","family":"Reis","sequence":"additional","affiliation":[{"name":"LIACC - Artificial Intelligence and Computer Science Lab FEUP - Faculty of Engineering of the University of Porto,Porto,Portugal"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"journal-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","year":"2017","author":"silver","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref14","article-title":"Temporal difference learning and TD-Gammon","author":"tesauro","year":"1995","journal-title":"Int Comput Game Assoc J"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"journal-title":"Dance Dance Revolution - Wikipedia The Free Encyclopedia","year":"2020","key":"ref16"},{"key":"ref4","first-page":"1804","author":"he","year":"0","journal-title":"Opponent modeling in deep reinforcement learning"},{"journal-title":"Adversarial policies Attacking deep reinforcement learning","year":"2019","author":"gleave","key":"ref3"},{"journal-title":"Stable Baselines","year":"2018","author":"hill","key":"ref6"},{"journal-title":"Emergence of locomotion behaviours in rich environments","year":"2017","author":"heess","key":"ref5"},{"journal-title":"Openai five","year":"2018","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"journal-title":"OpenAI Baselines","year":"2017","author":"dhariwal","key":"ref2"},{"journal-title":"EMERGENT COMPLEXITY VIA MULTI-AGENT COMPETITION","year":"2018","author":"bansal","key":"ref1"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref9"}],"event":{"name":"2022 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","start":{"date-parts":[[2022,4,29]]},"location":"Santa Maria da Feira, Portugal","end":{"date-parts":[[2022,4,30]]}},"container-title":["2022 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9784764\/9784765\/09784785.pdf?arnumber=9784785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:58:15Z","timestamp":1656363495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9784785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,29]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/icarsc55462.2022.9784785","relation":{},"subject":[],"published":{"date-parts":[[2022,4,29]]}}}