{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T02:32:30Z","timestamp":1768444350983,"version":"3.49.0"},"reference-count":33,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2022,8,31]],"date-time":"2022-08-31T00:00:00Z","timestamp":1661904000000},"content-version":"am","delay-in-days":365,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/onlinelibrary.wiley.com\/termsAndConditions#am"},{"start":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T00:00:00Z","timestamp":1630368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T00:00:00Z","timestamp":1630368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int J Intell Syst"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1002\/int.22648","type":"journal-article","created":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T16:30:39Z","timestamp":1630427439000},"page":"799-828","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Multi\u2010agent reinforcement learning via knowledge transfer with differentially private noise"],"prefix":"10.1155","volume":"37","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-0167-8975","authenticated-orcid":false,"given":"Zishuo","family":"Cheng","sequence":"first","affiliation":[{"name":"Centre of Cyber Security and Privacy, School of Computer Science University of Technology Sydney Ultimo New South Wales Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-7561-0992","authenticated-orcid":false,"given":"Dayong","family":"Ye","sequence":"additional","affiliation":[{"name":"Centre of Cyber Security and Privacy, School of Computer Science University of Technology Sydney Ultimo New South Wales Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-3411-7947","authenticated-orcid":false,"given":"Tianqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Centre of Cyber Security and Privacy, School of Computer Science University of Technology Sydney Ultimo New South Wales Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-1680-2521","authenticated-orcid":false,"given":"Wanlei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Data Science City University of Macau Macau Macao"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Illinois at Chicago Chicago Illinois USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Congcong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Centre of Cyber Security and Privacy, School of Computer Science University of Technology Sydney Ultimo New South Wales Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,8,31]]},"reference":[{"key":"e_1_2_12_2_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton RS","year":"2018"},{"key":"e_1_2_12_3_1","first-page":"503","article-title":"Tree\u2010based batch mode reinforcement learning","volume":"6","author":"Ernst D","year":"2005","journal-title":"J Mach Learn Res"},{"key":"e_1_2_12_4_1","unstructured":"TirinzoniA SessaA PirottaM RestelliM. Importance weighted transfer of samples in reinforcement learning. Proc. of ICML.2018."},{"key":"e_1_2_12_5_1","doi-asserted-by":"crossref","unstructured":"LarocheR BarlierM. Transfer reinforcement learning with shared dynamics. Proc. of AAAI.2017.","DOI":"10.1609\/aaai.v31i1.10796"},{"key":"e_1_2_12_6_1","doi-asserted-by":"crossref","unstructured":"DworkC. Differential privacy. Proc. of ICALP.2006:1\u201012.","DOI":"10.1007\/11787006_1"},{"key":"e_1_2_12_7_1","unstructured":"SuX ZhangM BaiQ YeD. Mation in disaster environments under spatial and communicational constraints. Workshops at the Twenty\u2010Eighth AAAI Conference on Artificial Intelligence.2014."},{"key":"e_1_2_12_8_1","unstructured":"ZhanY TaylorME. Online transfer learning in reinforcement learning domains. Proc. of the AAAI 2015 Fall Symposium USA.2015:97\u2010104."},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2543238"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"issue":"4","key":"e_1_2_12_11_1","first-page":"2165","article-title":"Agents teaching agents: a survey on inter\u2010agent transfer learning","volume":"34","author":"Silva FLD","year":"2019","journal-title":"Auton Agent Multi\u2010Agent Syst"},{"key":"e_1_2_12_12_1","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/978-3-642-27645-3_5","volume-title":"Transfer in Reinforcement Learning: A Framework and a Survey","author":"Lazaric A","year":"2012"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11316"},{"key":"e_1_2_12_14_1","unstructured":"AbelD JinnaiY GuoY KonidarisG LittmanML. Policy and value transfer in lifelong reinforcement learning. Proc. of ICML. 2018:2018."},{"key":"e_1_2_12_15_1","unstructured":"AmirO KamarE KolobovA GroszB. Interactive teaching strategies for agent training. Proc. of the 25th International Joint Conference on Artificial Intelligence (IJCAI).2016:804\u2010811."},{"key":"e_1_2_12_16_1","unstructured":"ClouseJA. Learning from an automated training agent. In:Adaptation and Learning in Multi\u2010agent Systems. Berlin: Springer Verlag;1996:9\u201016."},{"issue":"3","key":"e_1_2_12_17_1","first-page":"1","article-title":"Improving interactive reinforcement learning: what makes a good teacher?","volume":"30","author":"Cruz F","year":"2018","journal-title":"J Conn Sci"},{"key":"e_1_2_12_18_1","unstructured":"SilvadFL GlattR CostaAHR. Simultaneously learning and advising in multi\u2010agent reinforcement learning. Proc. of the 16th International Conference on Autonomous Agents and Multi\u2010agent Systems (AAMAS) Brazil.2017:1100\u20101108."},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/make1010002"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2014.885279"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa9375"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2697856"},{"key":"e_1_2_12_23_1","article-title":"More than privacy: applying differential privacy in key areas of artificial intelligence","author":"Zhu T","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2906574"},{"key":"e_1_2_12_25_1","article-title":"Differential advising in multi\u2010agent reinforcement learning","author":"Ye D","year":"2020","journal-title":"IEEE Trans Cybern"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2504350"},{"key":"e_1_2_12_27_1","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: a survey","volume":"10","author":"Taylor ME","year":"2009","journal-title":"J Mach Learn Res"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_12_29_1","doi-asserted-by":"crossref","unstructured":"LazaricA RestelliM BonariniA. Transfer of samples in batch reinforcement learning. Proc. of ICML.2008.","DOI":"10.1145\/1390156.1390225"},{"key":"e_1_2_12_30_1","doi-asserted-by":"crossref","unstructured":"McSherryF TalwarK. Mechanism design via differential privacy. Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science FOCS'07 Washington DC. IEEE Computer Society;2007:94\u2010103.","DOI":"10.1109\/FOCS.2007.66"},{"key":"e_1_2_12_31_1","doi-asserted-by":"crossref","unstructured":"LittmanML. Markov games as a framework for multi\u2010agent reinforcement learning. Proceedings of the Eleventh International Conference 1994. Morgan Kaufmann Publishers;1994:157\u2010163.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"e_1_2_12_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.06.003"},{"key":"e_1_2_12_33_1","unstructured":"Half field offense. An environment for multi\u2010agent learning and ad hoc teamwork. AAMAS Adaptive Learning Agents (ALA) Workshop;2016."},{"key":"e_1_2_12_34_1","unstructured":"AkiyamaH. RoboCup tools project.2012.https:\/\/2.zoppoz.workers.dev:443\/https\/osdn.jp\/projects\/rctools\/. Accessed August 1 2020."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/int.22648","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/int.22648","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/am-pdf\/10.1002\/int.22648","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/int.22648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T15:38:11Z","timestamp":1675957091000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/10.1002\/int.22648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,31]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["10.1002\/int.22648"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/int.22648","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,31]]},"assertion":[{"value":"2021-06-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}