{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:36:40Z","timestamp":1780666600945,"version":"3.54.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1109\/jcc56315.2022.00013","type":"proceedings-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T21:02:13Z","timestamp":1664226133000},"page":"37-42","source":"Crossref","is-referenced-by-count":9,"title":["Improving scalability of multi-agent reinforcement learning with parameters sharing"],"prefix":"10.1109","author":[{"given":"Ning","family":"Yang","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,Changsha"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,Changsha"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"PeiChang","family":"Shi","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,Changsha"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science,Changsha"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Sharing knowledge in multi-task deep reinforcement learning","author":"d\u2019eramo","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref11","article-title":"Distral: Robust multitask reinforcement learning","volume":"30","author":"teh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"2020","article-title":"Phasic policy gradient","author":"cobbe","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref13","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref14","article-title":"Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning","volume":"34","author":"yang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","author":"iqbal","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"arXiv preprint arXiv 1902 09080"},{"key":"ref17","author":"yang","year":"2020","journal-title":"arXiv preprint arXiv 2011 00177"},{"key":"ref18","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Dop: Off-policy multi-agent decomposed policy gradients","author":"wang","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref3","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems ser NIPS’17"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142402"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"ref8","author":"wakilpoor","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref2","author":"wang","year":"2020","journal-title":"arXiv preprint arXiv 2008 06439"},{"key":"ref1","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref9","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","author":"christianos","year":"2021","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 IEEE International Conference on Joint Cloud Computing (JCC)","location":"Fremont, CA, USA","start":{"date-parts":[[2022,8,15]]},"end":{"date-parts":[[2022,8,18]]}},"container-title":["2022 IEEE International Conference on Joint Cloud Computing (JCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897094\/9898078\/09898089.pdf?arnumber=9898089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:51:55Z","timestamp":1665780715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9898089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/jcc56315.2022.00013","relation":{},"subject":[],"published":{"date-parts":[[2022,8]]}}}