{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:54:40Z","timestamp":1771700080162,"version":"3.50.1"},"reference-count":34,"publisher":"Zhejiang University Press","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front Inform Technol Electron Eng"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1631\/fitee.2100594","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T07:04:03Z","timestamp":1658732643000},"page":"1032-1042","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Coach-assisted multi-agent reinforcement learning framework for unexpected crashed agents","\u9488\u5bf9\u610f\u5916\u5d29\u6e83\u667a\u80fd\u4f53\u7684\u6559\u7ec3\u8f85\u52a9\u591a\u667a\u80fd\u4f53\u5f3a\u5316\u5b66\u4e60\u6846\u67b6"],"prefix":"10.1631","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-990X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youpeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunhan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"635","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9196540"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tsmcc.2007.913919"},{"key":"ref3","first-page":"1","article-title":"Carla: an open urban driving simulator","volume-title":"Proc 1st Conf on Robot Learning","author":"Dosovitskiy","year":"2017"},{"key":"ref4","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc 34th Int Conf on Machine Learning","author":"Foerster","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"},{"key":"ref6","first-page":"1523","article-title":"Multiagent planning with factored MDPs","volume-title":"Proc 14th Int Conf on Neural Information Processing Systems: Natural and Synthetic","author":"Guestrin","year":"2001"},{"key":"ref7","first-page":"1480","article-title":"DARLA: improving zero-shot transfer in reinforcement learning","volume-title":"Proc 34th Int Conf on Machine Learning","author":"Higgins","year":"2017"},{"key":"ref8","first-page":"1","article-title":"Learning to schedule communication in multi-agent reinforcement learning","volume-title":"Proc 7th Int Conf on Learning Representations","author":"Kim","year":"2019"},{"key":"ref9","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"Kok","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref11","first-page":"6382","article-title":"Multi-agent actorcritic for mixed cooperative-competitive environments","volume-title":"Proc 31st Int Conf on Neural Information Processing Systems","author":"Lowe","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ecmr.2019.8870934"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"181","key":"ref14","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: a framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref16","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc 34th Int Conf on Machine Learning","author":"Omidshafiei","year":"2017"},{"key":"ref17","first-page":"2681","article-title":"Multiagent bidirectionally-coordinated nets: emergence of human-level coordination in learning to play starcraft combat games","volume-title":"Proc 34th Int Conf on Machine Learning","author":"Peng","year":"2017"},{"key":"ref18","first-page":"4292","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc 35th Int Conf on Machine Learning","author":"Rashid","year":"2018"},{"key":"ref19","first-page":"2186","article-title":"The StarCraft Multi-agent Challenge","volume-title":"Proc 18th Int Conf on Autonomous Agents and Multiagent Systems","author":"Samvelyan","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref21","first-page":"5887","article-title":"QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc 36th Int Conf on Machine Learning","author":"Son","year":"2019"},{"key":"ref22","first-page":"2252","article-title":"Learning multi-agent communication with backpropagation","volume-title":"Proc 30th Int Conf on Neural Information Processing Systems","author":"Sukhbaatar","year":"2016"},{"key":"ref23","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc 17th Int Conf on Autonomous Agents and Multiagent Systems","author":"Sunehag","year":"2018"},{"key":"ref24","first-page":"330","article-title":"Multi-agent Reinforcement Learning: Independent vs","volume-title":"Cooperative Agents","author":"Tan","year":"1993"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2017.8202133"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2012.6386109"},{"key":"ref27","volume-title":"Continual reinforcement learning deployed in real-life using policy distillation and Sim2Real transfer","author":"Traor\u00e9","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v33i3.2426"},{"key":"ref29","first-page":"1","article-title":"QPLEX: duplex dueling multi-agent Q-learning","volume-title":"Proc 9th Int Conf on Learning Representations","author":"Wang","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1900308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1900637"},{"key":"ref32","volume-title":"QATTEN: a general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1900661"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ssci47803.2020.9308468"}],"container-title":["Frontiers of Information Technology & Electronic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2100594.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1631\/FITEE.2100594\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2100594.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:38:17Z","timestamp":1771655897000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1631\/FITEE.2100594"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":34,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["1828"],"URL":"https:\/\/doi.org\/10.1631\/fitee.2100594","relation":{},"ISSN":["2095-9184","2095-9230"],"issn-type":[{"value":"2095-9184","type":"print"},{"value":"2095-9230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]},"assertion":[{"value":"31 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}