{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:23:24Z","timestamp":1740101004174,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":["2018AAA0101005,2018AAA0102402"],"award-info":[{"award-number":["2018AAA0101005,2018AAA0102402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27030204"],"award-info":[{"award-number":["XDA27030204"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892092","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Intrinsic Reward with Peer Incentives for Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Tianle","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Shiguang","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]},{"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.5751\/ES-03564-1504r01"},{"key":"ref11","article-title":"Deception in social learning: A multi-agent reinforce-ment learning perspective","author":"chelarescu","year":"2021","journal-title":"ArXiv Preprint"},{"year":"2016","author":"veroff","journal-title":"Social incentives A life-span developmental approach","key":"ref12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1111\/j.1467-937X.2005.00342.x"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1016\/j.geb.2008.11.004"},{"key":"ref15","first-page":"2186","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref16","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":"ref17","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"},{"key":"ref18","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref19","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref3","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref5","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"},{"year":"2019","author":"du","journal-title":"Liir Learning individual intrinsic reward in multi-agent reinforcement learning","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1017\/S0269888918000292"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TVT.2020.2997896"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref9","first-page":"789","article-title":"Gifting in multi-agent reinforcement learning","author":"lupu","year":"2020","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"ref22","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Learning individually inferred commu-nication for multi-agent cooperation","author":"ding","year":"2020","journal-title":"ArXiv Preprint"},{"year":"2016","author":"pearl","journal-title":"Causal Inference in Statistics A Primer","key":"ref23"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892092.pdf?arnumber=9892092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:39:55Z","timestamp":1670283595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892092\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892092","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}