{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:50:47Z","timestamp":1766137847640,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"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":[[2021,8,17]]},"DOI":"10.1109\/cog52621.2021.9619002","type":"proceedings-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:53:06Z","timestamp":1638910386000},"page":"01-08","source":"Crossref","is-referenced-by-count":11,"title":["MAIDRL: Semi-centralized Multi-Agent Reinforcement Learning using Agent Influence"],"prefix":"10.1109","author":[{"given":"Anthony","family":"Harris","sequence":"first","affiliation":[]},{"given":"Siming","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Multiagent bidirectionally-coordinated nets: emergence of human-level coordination in learning to play StarCraft combat games","author":"peng","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref13","first-page":"103","article-title":"A framework for behavioural cloning","volume":"15","author":"bain","year":"1995","journal-title":"Machine Intelligence"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2020.08.012"},{"key":"ref15","article-title":"Scaling imitation learning in Minecraft","author":"amiranashvili","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref17","first-page":"278","article-title":"Policy invariance under reward transformations: theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref18","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"An analysis of model-based heuristic search techniques for StarCraft combat scenarios","volume":"13","author":"churchill","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment"},{"key":"ref4","article-title":"The StarCraft multi-agent challenge","volume":"abs 1902 4043","author":"samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042943"},{"key":"ref6","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref5","first-page":"1008","article-title":"Actor-Critic algorithms","author":"konda","year":"2000","journal-title":"Advances in Neural Information Processing Systems Citeseer"},{"key":"ref8","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"Emergence of grounded compositional language in multi-agent populations","volume":"32","author":"mordatch","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref2","article-title":"Multi-agent Actor-Critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"ArXiv Preprint"},{"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","article-title":"Counterfactual multi-agent policy gradients","volume":"32","author":"foerster","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref20","first-page":"1371","article-title":"Comparing heuristic search methods for finding effective group behaviors in rts game","author":"liu","year":"2013","journal-title":"2013 IEEE Congress on Evolutionary Computation"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633643"},{"key":"ref21","first-page":"1","article-title":"Using CIGAR for finding effective group behaviors in rts game","year":"0","journal-title":"2013 IEEE Conference on Computational Intelligence in Games (CIG)"},{"key":"ref24","article-title":"Relational deep reinforcement learning","author":"zambaldi","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0743-1066(94)90035-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"}],"event":{"name":"2021 IEEE Conference on Games (CoG)","start":{"date-parts":[[2021,8,17]]},"location":"Copenhagen, Denmark","end":{"date-parts":[[2021,8,20]]}},"container-title":["2021 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9618888\/9618891\/09619002.pdf?arnumber=9619002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:53:35Z","timestamp":1652201615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9619002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,17]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/cog52621.2021.9619002","relation":{},"subject":[],"published":{"date-parts":[[2021,8,17]]}}}