{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:15:56Z","timestamp":1779099356334,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000},"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":[[2023,7,3]]},"DOI":"10.1109\/codit58514.2023.10284342","type":"proceedings-article","created":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T17:46:12Z","timestamp":1698169572000},"page":"2514-2518","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Agent Reinforcement Learning with Epistemic Priors"],"prefix":"10.1109","author":[{"given":"Thayne T.","family":"Walker","sequence":"first","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime S.","family":"Ide","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minkyu","family":"Choi","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Guarino","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Alcedo","sequence":"additional","affiliation":[{"name":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Modeling others using oneself in multi-agent reinforcement learning","author":"raileanu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref24","first-page":"24 611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"yu","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v12i1.18584"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.4204\/EPTCS.243.6"},{"key":"ref14","author":"zalta","year":"1995","journal-title":"Stanford Encyclopedia of Philosophy"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6219"},{"key":"ref11","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9665"},{"key":"ref10","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2972"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3166\/jancl.21.9-34"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X00076512"},{"key":"ref17","first-page":"255","article-title":"A multi-agent reinforcement learning method with the estimation of the other agent's actions","volume":"1","author":"nagayuki","year":"2000","journal-title":"Proceedings of the Fifth International Symposium on Artificial Life and Robotics"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2514\/6.2021-1267"},{"key":"ref19","article-title":"Beating the defense: Using plan recognition to inform learning agents","author":"molineaux","year":"2009","journal-title":"KNEXUS RE-SEARCH CORP SPRINGFIELD VA Tech Rep"},{"key":"ref18","author":"administration","year":"2022","journal-title":"Faa order jo 7110 65z - air traffic control"},{"key":"ref8","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8380"},{"key":"ref4","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"}],"event":{"name":"2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)","location":"Rome, Italy","start":{"date-parts":[[2023,7,3]]},"end":{"date-parts":[[2023,7,6]]}},"container-title":["2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10284032\/10284045\/10284342.pdf?arnumber=10284342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T18:45:13Z","timestamp":1750099513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10284342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,3]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/codit58514.2023.10284342","relation":{},"subject":[],"published":{"date-parts":[[2023,7,3]]}}}