{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:24:48Z","timestamp":1730301888044,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T00:00:00Z","timestamp":1719187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T00:00:00Z","timestamp":1719187200000},"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":[[2024,6,24]]},"DOI":"10.1109\/ur61395.2024.10597441","type":"proceedings-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T17:23:58Z","timestamp":1722014638000},"page":"251-256","source":"Crossref","is-referenced-by-count":0,"title":["Relational Q-Functionals: Multi-Agent Learning to Recover from Unforeseen Robot Malfunctions in Continuous Action Domains"],"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"}]},{"given":"Paul","family":"Robinette","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Department of Electrical and Computer Engineering,Lowell,MA,USA"}]},{"given":"Kshitij","family":"Jerath","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Department of Mechanical Engineering,Lowell,MA,USA"}]},{"given":"Reza","family":"Azadeh","sequence":"additional","affiliation":[{"name":"Richard Miner School of Computer and Information Sciences, University of Massachusetts,PeARL Lab,Lowell,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831228"},{"issue":"54","key":"ref2","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"},{"issue":"1","key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref9","first-page":"1","article-title":"Collaborative adaptation: Learning to recover from unforeseen malfunctions in multi-robot teams","volume-title":"MADGames workshop at IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA","author":"Findik","year":"2023"},{"journal-title":"Gymnasium robotics","year":"2023","author":"de Lazcano","key":"ref10"},{"issue":"746\u2013752","key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref14","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"Hernandez-Leal","year":"2017","journal-title":"arXiv preprint"},{"key":"ref15","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":"ref16","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":"ref17","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv preprint"},{"issue":"1","key":"ref18","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":"ref19","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"},{"key":"ref20","article-title":"Learning with opponent-learning awareness","author":"Foerster","year":"2017","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383543"},{"key":"ref22","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref24","article-title":"Actor-expert: A framework for using q-learning in continuous action spaces","volume":"9","author":"Lim","year":"2018","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26073"},{"key":"ref26","article-title":"Mixed q-functionals: Advancing value-based methods in cooperative marl with continuous action domains","author":"Findik","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"12 208","article-title":"Facmac: Factored multi-agent centralised policy gradients","volume":"34","author":"Peng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 21st International Conference on Ubiquitous Robots (UR)","start":{"date-parts":[[2024,6,24]]},"location":"New York, NY, USA","end":{"date-parts":[[2024,6,27]]}},"container-title":["2024 21st International Conference on Ubiquitous Robots (UR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10597436\/10597437\/10597441.pdf?arnumber=10597441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T05:28:31Z","timestamp":1722058111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10597441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,24]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ur61395.2024.10597441","relation":{},"subject":[],"published":{"date-parts":[[2024,6,24]]}}}