{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:58:04Z","timestamp":1775098684987,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100005542","name":"CAS","doi-asserted-by":"publisher","award":["JCPYJJ-22017"],"award-info":[{"award-number":["JCPYJJ-22017"]}],"id":[{"id":"10.13039\/100005542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876181"],"award-info":[{"award-number":["61876181"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Science","doi-asserted-by":"publisher","award":["QYZDB-SSW-JSC006"],"award-info":[{"award-number":["QYZDB-SSW-JSC006"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191476","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Explicitly Learning Policy Under Partial Observability in Multiagent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Chen","family":"Yang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangkai","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junge","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref2","article-title":"Guided deep reinforcement learning for swarm systems","author":"H\u00fcttenrauch","year":"2017","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref4","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Starcraft ii: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref9","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid","year":"2018"},{"key":"ref10","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"10199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Qplex: Duplex dueling multi-agent q-learning","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016062"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17420"},{"key":"ref15","first-page":"1942","article-title":"Bayesian action decoder for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Foerster","year":"2019"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref18","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref20","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref22","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","first-page":"1023","article-title":"Acting optimally in partially observable stochastic domains","volume":"94","author":"Cassandra","year":"1994","journal-title":"Aaai"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref26","article-title":"Liir: Learning individual intrinsic reward in multi-agent reinforcement learning","volume":"32","author":"Du","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume":"33","author":"Zhou","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref29","article-title":"Do deep nets really need to be deep?","volume":"27","author":"Ba","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Deep model compression: Distilling knowledge from noisy teachers","author":"Sau","year":"2016","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Policy distillation","author":"Rusu","year":"2015","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"A new framework for multi-agent reinforcement learning-centralized training and exploration with decentralized execution via policy distillation","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967849"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref35","article-title":"Deep recurrent q-learning for partially observable mdps","volume-title":"2015 aaai fall symposium series","author":"Hausknecht"},{"key":"ref36","article-title":"Hypernetworks","author":"Ha","year":"2016","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"On multiplicative integration with recurrent neural networks","volume":"29","author":"Wu","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","location":"Gold Coast, Australia","start":{"date-parts":[[2023,6,18]]},"end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191476.pdf?arnumber=10191476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T15:27:20Z","timestamp":1709306840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191476","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}