{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T10:26:27Z","timestamp":1758709587579,"version":"3.37.3"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Tsinghua EE Xilinx AI Research Fund"},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center For Information Science And Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2019, 61832007"],"award-info":[{"award-number":["U19B2019, 61832007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Innovation Center for Future Chips"},{"name":"National Key Research and Development Program of China","award":["2017YFA0207600"],"award-info":[{"award-number":["2017YFA0207600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3085328","type":"journal-article","created":{"date-parts":[[2021,6,3]],"date-time":"2021-06-03T03:43:25Z","timestamp":1622691805000},"page":"84773-84782","source":"Crossref","is-referenced-by-count":3,"title":["Low-Cost Multi-Agent Navigation via Reinforcement Learning With Multi-Fidelity Simulator"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1328-2639","authenticated-orcid":false,"given":"Jiantao","family":"Qiu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiling","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianxiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6556-7468","authenticated-orcid":false,"given":"Jincheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-353X","authenticated-orcid":false,"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref13","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"kahn","year":"2017","journal-title":"arXiv 1702 01182"},{"key":"ref14","first-page":"1995","article-title":"Coordinated multi-agent imitation learning","author":"le","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref15","first-page":"7461","article-title":"Multi-agent generative adversarial imitation learning","author":"song","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref18","article-title":"Progressive neural networks","author":"rusu","year":"2016","journal-title":"arXiv 1606 04671"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref5","first-page":"8224","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"buckman","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487756"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2419431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915576234"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8664803"},{"key":"ref20","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09445074.pdf?arnumber=9445074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:23Z","timestamp":1639770983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9445074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3085328","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}