{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:19:48Z","timestamp":1776885588728,"version":"3.51.2"},"reference-count":25,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102404"],"award-info":[{"award-number":["2018AAA0102404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136008"],"award-info":[{"award-number":["62136008"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","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\/ijcnn54540.2023.10191652","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":1,"title":["Advantage Constrained Proximal Policy Optimization in Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Weifan","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref15","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"ref11","article-title":"A natural policy gradient","volume":"14","author":"kakade","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"A survey of deep rein- forcement learning in video games","author":"shao","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2016.2641929"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3083410"},{"key":"ref17","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","author":"kuba","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref16","first-page":"13 458","article-title":"Settling the variance of multi-agent policy gradients","volume":"34","author":"kuba","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref18","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de witt","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Deep multi-agent reinforcement learning for decentralized continuous cooperative control","volume":"19","author":"de witt","year":"0","journal-title":"ArXiv Preprint"},{"key":"ref23","first-page":"12 208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume":"34","author":"peng","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"2186","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref20","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref22","article-title":"{QPLEX}: Duplex dueling multi-agent q-learning","author":"wang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref21","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179775"},{"key":"ref9","article-title":"Unmas: Multiagent reinforcement learning for unshaped cooperative scenarios","author":"chai","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280949"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.3042244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI44817.2019.9003120"}],"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\/10191652.pdf?arnumber=10191652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:44:22Z","timestamp":1692639862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191652","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}