{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:35:26Z","timestamp":1763811326009,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2112633"],"award-info":[{"award-number":["IIS-2112633"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Lab","doi-asserted-by":"publisher","award":["W911NF20-2-0089"],"award-info":[{"award-number":["W911NF20-2-0089"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383543","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"4447-4454","source":"Crossref","is-referenced-by-count":5,"title":["Impact of Relational Networks in Multi-Agent Learning: A Value-Based Factorization View"],"prefix":"10.1109","author":[{"given":"Yasin","family":"Findik","sequence":"first","affiliation":[{"name":"Richard Miner School of Computer and Information Sciences, University of Massachusetts,PeARL Lab,Lowell,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Robinette","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Department of Electrical and Computer Engineering,Lowell,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kshitij","family":"Jerath","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Department of Mechanical Engineering,Lowell,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Reza","family":"Ahmadzadeh","sequence":"additional","affiliation":[{"name":"Richard Miner School of Computer and Information Sciences, University of Massachusetts,PeARL Lab,Lowell,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281867"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/machines5010006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3059237"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1115\/1.4046580"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/s0269888912000057"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref11","article-title":"Multiagent planning with factored mdps","volume":"14","author":"Guestrin","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"980","article-title":"Deep coordination graphs","volume-title":"International Conference on Machine Learning","author":"B\u00f6hmer","year":"2020"},{"key":"ref13","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv preprint"},{"issue":"746\u2013752","key":"ref14","first-page":"2","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume":"1998","author":"Claus","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref18","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"Hernandez-Leal","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"International Conference on Machine Learning","author":"Zhang","year":"2018"},{"key":"ref20","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":"ref21","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"issue":"1","key":"ref22","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref23","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Son","year":"2019"},{"key":"ref24","first-page":"15786","article-title":"Emergent reciprocity and team formation from randomized uncertain social preferences","volume":"33","author":"Baker","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Reward-sharing relational networks in multi-agent reinforcement learning as a framework for emergent behavior","author":"Haeri","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"volume-title":"ma-gym: Collection of multi-agent environments based on openai gym","year":"2019","author":"Koul","key":"ref27"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383543.pdf?arnumber=10383543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:35:01Z","timestamp":1706027701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383543","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}