{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:40:47Z","timestamp":1776886847604,"version":"3.51.2"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096125","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Progressive Diversifying Policy for Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Shaoqi","family":"Sun","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhao","family":"Zhai","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref12","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref14","article-title":"The infinite gaussian mixture model","volume":"12","author":"rasmussen","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"yu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","author":"oliehoek","year":"2016","journal-title":"A Concise Introduction to Decentralized POMDPs"},{"key":"ref21","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"arXiv preprint arXiv 1810 12894"},{"key":"ref2","article-title":"Coordinated multi-robot exploration under communication constraints using decentralized markov decision processes","author":"matignon","year":"2012","journal-title":"Twenty-Sixth AAAI Conference on Artificial Intelligence"},{"key":"ref1","author":"singh","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2004.1365067"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/1118101"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759651"},{"key":"ref18","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"arXiv preprint arXiv 2103 01014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/int.22594"},{"key":"ref9","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2906260"},{"key":"ref6","first-page":"23417","article-title":"Individual reward assisted multi-agent reinforcement learning","author":"wang","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref5","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume":"34","author":"chenghao","year":"2021","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096125.pdf?arnumber=10096125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T17:45:40Z","timestamp":1751651140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096125","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}