{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T08:52:13Z","timestamp":1765356733516,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea funded by the Korea Government through the Ministry of Science and ICT","doi-asserted-by":"publisher","award":["NRF-2019R1A4A1024732"],"award-info":[{"award-number":["NRF-2019R1A4A1024732"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003561","name":"Ministry of Culture, Sports, and Tourism","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003561","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006465","name":"Korea Creative Content Agency, through the Culture Technology Research and Development Program, in 2019","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3007219","type":"journal-article","created":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T20:36:23Z","timestamp":1594067783000},"page":"125389-125400","source":"Crossref","is-referenced-by-count":14,"title":["Cooperative Multi-Agent Reinforcement Learning With Approximate Model Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3950-3065","authenticated-orcid":false,"given":"Young Joon","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young Jae","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2205-8516","authenticated-orcid":false,"given":"Seoung Bum","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Disentangling dynamics and returns: Value function decomposition with future prediction","author":"tang","year":"2019","journal-title":"arXiv 1905 11100"},{"key":"ref38","article-title":"Hierarchical deep multiagent reinforcement learning with temporal abstraction","author":"tang","year":"2018","journal-title":"arXiv 1809 09332"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1038\/nature16961"},{"key":"ref32","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc ICLR"},{"key":"ref31","first-page":"1","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc ICML"},{"key":"ref30","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 1703 10069"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref35","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc ICML"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1613\/jair.1427"},{"key":"ref40","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref11","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc ICML"},{"key":"ref12","first-page":"1523","article-title":"Multiagent planning with factored MDPS","volume":"14","author":"guestrin","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref14","first-page":"242","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","volume":"98","author":"hu","year":"1998","journal-title":"Proc 15th Int Conf Mach Learn"},{"key":"ref15","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume":"97","author":"iqbal","year":"2019","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1126\/science.aau6249"},{"key":"ref17","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017","journal-title":"Proc ICLR"},{"key":"ref18","article-title":"Model-based reinforcement learning for Atari","author":"kaiser","year":"2019","journal-title":"arXiv 1903 00374"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1016\/j.neucom.2016.01.031"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICRA.2018.8463189"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1613\/jair.4818"},{"key":"ref27","first-page":"1495","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2018","journal-title":"Proc AAAI"},{"key":"ref3","first-page":"1","article-title":"Learning internal state models in partially observable environments","author":"baisero","year":"2018","journal-title":"Proc Reinforcement Learn Under Partial Observability NeurIPS"},{"key":"ref6","first-page":"807","article-title":"All learning is local: Multi-agent learning in global reward games","volume":"16","author":"chang","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1613\/jair.2447"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref8","first-page":"1","article-title":"Efficient model-based deep reinforcement learning with variational state tabulation","author":"cornell","year":"2018","journal-title":"Proc ICML"},{"key":"ref7","first-page":"703","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","volume":"70","author":"chebotar","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1613\/jair.2575"},{"key":"ref9","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1613\/jair.1.11418"},{"key":"ref46","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1613\/jair.1.11244"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1016\/j.eswa.2005.04.039"},{"key":"ref22","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/TCYB.2019.2927410"},{"key":"ref42","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","author":"yang","year":"2020","journal-title":"arXiv 2002 03950"},{"key":"ref24","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref41","article-title":"R-MADDPG for partially observable environments and limited communication","author":"wang","year":"2020","journal-title":"arXiv 2002 06684"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/JAS.2020.1003072"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.3390\/s150510026"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref43","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"yang","year":"2020","journal-title":"arXiv 2002 03939"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1023\/A:1008819414322"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09133381.pdf?arnumber=9133381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T01:09:48Z","timestamp":1641949788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9133381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3007219","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}