{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:25:47Z","timestamp":1775816747022,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Science and Technology Research Project of the Jiangxi Education Department","award":["GJJ180442"],"award-info":[{"award-number":["GJJ180442"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2977400","type":"journal-article","created":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T20:52:20Z","timestamp":1583182340000},"page":"43098-43110","source":"Crossref","is-referenced-by-count":6,"title":["Risk Aversion Operator for Addressing Maximization Bias in Q-Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-0148","authenticated-orcid":false,"given":"Bi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0553-8569","authenticated-orcid":false,"given":"Xuelian","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7381-9349","authenticated-orcid":false,"given":"Zhiqiang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2417-6567","authenticated-orcid":false,"given":"Yangjun","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proc Connectionist Models Summer School"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50035-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21236\/ADA280862"},{"key":"ref30","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref35","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref34","first-page":"41","article-title":"Double delayed Q-learning","volume":"16","author":"abed-alguni","year":"2018","journal-title":"Artific Intellig Int J"},{"key":"ref10","first-page":"3223","article-title":"Deep Q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref11","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","volume":"70","author":"asadi","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref12","first-page":"9949","article-title":"Non-delusional Q-learning and value-iteration","author":"lu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614994"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04182-3_49"},{"key":"ref15","first-page":"2613","article-title":"Double Q-learning","author":"hasselt","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/483"},{"key":"ref17","first-page":"1073","article-title":"A generalization error for Q-learning","volume":"6","author":"murphy","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref18","first-page":"1476","article-title":"Increasing the action gap: New operators for reinforcement learning","author":"bellemare","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref19","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2935463"},{"key":"ref27","first-page":"4863","article-title":"Is Q-learning provably efficient?","author":"jin","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"2318","article-title":"Stochastic variance reduction for deep Q-learning","author":"zhao","year":"2019","journal-title":"Proc 18th Int Conf Auto Agents MultiAgent Syst Int Found Auton Agents Multiagent Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1080.0324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2945060"},{"key":"ref8","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref7","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref2","article-title":"Visceral machines: Risk-aversion in reinforcement learning with intrinsic physiological rewards","author":"mcduff","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref1","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref20","volume":"190","author":"bucklew","year":"1990","journal-title":"Large Deviation Techniques in Decision Simulation and Estimation"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/2951719"},{"key":"ref21","author":"moore","year":"1993","journal-title":"Introduction to the Practice of Statistics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"ref23","first-page":"2411","article-title":"Speedy Q-learning","author":"ghavamzadeh","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"202","article-title":"Taming the noise in reinforcement learning via soft updates","author":"fox","year":"2016","journal-title":"Proc Conf Uncertainty in Artif Intell (UAI)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09019603.pdf?arnumber=9019603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T19:55:20Z","timestamp":1662666920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9019603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2977400","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}