{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:22Z","timestamp":1755993742716,"version":"3.44.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019827","name":"Meta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019827","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004351","name":"Cisco Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004351","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2114415"],"award-info":[{"award-number":["2114415"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tai.2022.3195818","type":"journal-article","created":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T17:54:49Z","timestamp":1659462889000},"page":"1141-1153","source":"Crossref","is-referenced-by-count":3,"title":["Learning Multiagent Options for Tabular Reinforcement Learning using Factor Graphs"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7708-5247","authenticated-orcid":false,"given":"Jiayu","family":"Chen","sequence":"first","affiliation":[{"name":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3010-8090","authenticated-orcid":false,"given":"Tian","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, George Washington University, Washington, DC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-4723","authenticated-orcid":false,"given":"Vaneet","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"School of Industrial Engineering and the School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IMSCCS.2006.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11418"},{"key":"ref34","first-page":"11003","article-title":"Towards better Laplacian representation in reinforcement learning with generalized graph drawing","author":"wang","year":"0","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref15","article-title":"Learning to coordinate manipulation skills via skill behavior diversification","author":"lee","year":"0","journal-title":"Proc 8th Int Conf Learn Represent"},{"key":"ref37","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"0","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref14","first-page":"1792","article-title":"Option-critic in cooperative multi-agent systems","author":"chakravorty","year":"0","journal-title":"Proc 19th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1962-0133816-6"},{"key":"ref30","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"0","journal-title":"Proc 7th Int Conf Learn Represent"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11418"},{"key":"ref33","article-title":"The Laplacian in RL: Learning representations with efficient approximations","author":"wu","year":"0","journal-title":"Proc 7th Int Conf Learn Represent"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377282"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.082"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc 4th Int Conf Learn Represent"},{"article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","year":"2018","author":"ebert","key":"ref1"},{"key":"ref17","first-page":"576","article-title":"Exploration-exploitation in MDPs with options","author":"fruit","year":"0","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"journal-title":"Reinforcement Learning—An Introduction","year":"1998","author":"sutton","key":"ref39"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/072342a0"},{"key":"ref19","first-page":"109:1","article-title":"Hierarchical reinforcement learning: A comprehensive survey","volume":"54","author":"pateria","year":"2021","journal-title":"ACM Comput Surv"},{"key":"ref18","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45622-8_16"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11831"},{"key":"ref45","volume":"2","author":"west","year":"2001","journal-title":"Introduction to Graph Theory"},{"key":"ref26","first-page":"1497","article-title":"Skill characterization based on betweenness","author":"simsek","year":"0","journal-title":"Proc 22nd Int Conf Neural Inf Process Syst"},{"key":"ref25","first-page":"816","article-title":"Identifying useful subgoals in reinforcement learning by local graph partitioning","author":"simsek","year":"0","journal-title":"Proc 22nd Int Conf Mach Learn"},{"key":"ref20","first-page":"361","article-title":"Automatic discovery of subgoals in reinforcement learning using diverse density","author":"mcgovern","year":"0","journal-title":"Proc 8th Int Conf Mach Learn"},{"key":"ref42","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","author":"mahajan","year":"0","journal-title":"Proc 33th Int Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref22","first-page":"1588","article-title":"Adaptive skills adaptive partitions (ASAP)","author":"mankowitz","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.dam.2015.12.006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36755-1_25"},{"article-title":"Multi-agent option discovery based on Kronecker product","year":"2022","author":"chen","key":"ref43"},{"key":"ref28","article-title":"Eigenoption discovery through the deep successor representation","author":"machado","year":"0","journal-title":"Proc 6th Int Conf Learn Represent"},{"key":"ref27","first-page":"2295","article-title":"A Laplacian framework for option discovery in reinforcement learning","author":"machado","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref29","first-page":"1566","article-title":"Hierarchical cooperative multi-agent reinforcement learning with skill discovery","author":"yang","year":"0","journal-title":"Proc 19th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref8","first-page":"3130","article-title":"Discovering options for exploration by minimizing cover time","author":"jinnai","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref7","first-page":"3120","article-title":"Finding options that minimize planning time","author":"jinnai","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21136\/CMJ.1973.101168"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"article-title":"Playing Atari games with deep reinforcement learning and human checkpoint replay","year":"2016","author":"hosu","key":"ref5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9078688\/10261321\/9847387-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10261321\/09847387.pdf?arnumber=9847387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:41Z","timestamp":1755911321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9847387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":45,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3195818","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}