{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T04:52:59Z","timestamp":1749099179902,"version":"3.37.3"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Defense Science and Technology Key Laboratory Fund","award":["6142103190308"],"award-info":[{"award-number":["6142103190308"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["G2019KY05201"],"award-info":[{"award-number":["G2019KY05201"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tcds.2021.3110959","type":"journal-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:22:45Z","timestamp":1632342165000},"page":"1486-1495","source":"Crossref","is-referenced-by-count":10,"title":["A Dynamically Adaptive Approach to Reducing Strategic Interference for Multiagent Systems"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8623-2341","authenticated-orcid":false,"given":"Wei","family":"Pan","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"given":"Nanding","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"given":"Chenxi","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9234-4836","authenticated-orcid":false,"given":"Kao-Shing","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9162923"},{"key":"ref11","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref15","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref16","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"1331","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206879"},{"key":"ref28","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref4","first-page":"1026","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc IEEE Int Conf Learn Represent"},{"key":"ref27","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref6","first-page":"2201","article-title":"The importance of experience replay database composition in deep reinforcement learning","author":"bruin","year":"2015","journal-title":"Proc Deep Reinforcement Learn Workshop (NIPS)"},{"key":"ref29","first-page":"2875","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"ackermann","year":"2019","journal-title":"Proc NeurIPS Deep RL Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2984033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376302"},{"key":"ref1","first-page":"529","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"et al"},{"key":"ref20","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Advances in Neural Information Processing Systems 29 (NIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399095"},{"key":"ref21","first-page":"464","article-title":"Multi-agent reinforcement learning in sequential social dilemmas","author":"leibo","year":"2017","journal-title":"Proc 16th Int Conf Auton Agents Multi-Agent Syst (AAMAS)"},{"key":"ref24","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1160633.1160776"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00123"},{"key":"ref25","first-page":"443","article-title":"Lenient multi-agent deep reinforcement learning","author":"palmer","year":"2018","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9976403\/09544063.pdf?arnumber=9544063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:09:09Z","timestamp":1672081749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9544063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":29,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2021.3110959","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}