{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:42Z","timestamp":1740169242651,"version":"3.37.3"},"reference-count":46,"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"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100013285","name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013285","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3128558","type":"journal-article","created":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T20:31:06Z","timestamp":1637094666000},"page":"154600-154611","source":"Crossref","is-referenced-by-count":1,"title":["NAEM: Noisy Attention Exploration Module for Deep Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9557-715X","authenticated-orcid":false,"given":"Zhenwen","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9021-136X","authenticated-orcid":false,"given":"Feifei","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6914-1547","authenticated-orcid":false,"given":"Chunyan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4395-9978","authenticated-orcid":false,"given":"Koji","family":"Kotani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3079-9207","authenticated-orcid":false,"given":"Qiu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Relational deep reinforcement learning","author":"zambaldi","year":"2018","journal-title":"arXiv 1806 01830"},{"key":"ref38","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume":"70","author":"bellemare","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref33","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnja","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref32","first-page":"9397","article-title":"Taylor expansion policy optimization","volume":"119","author":"tang","year":"2020","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref31","article-title":"Mirror descent policy optimization","author":"tomar","year":"2020","journal-title":"arXiv 2005 09814"},{"key":"ref30","first-page":"1104","article-title":"Implicit quantile networks for distributional reinforcement learning","volume":"80","author":"dabney","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref36","first-page":"11204","article-title":"Provably convergent two-timescale off-policy actor-critic with function approximation","volume":"119","author":"zhang","year":"2020","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref35","first-page":"1999","article-title":"Generalized off-policy actor-critic","author":"zhang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","article-title":"Soft actor-critic for discrete action settings","author":"christodoulou","year":"2019","journal-title":"arXiv 1910 07207"},{"key":"ref10","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","author":"azar","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3389847"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref14","first-page":"1","article-title":"Towards playing full MOBA games with deep reinforcement learning","author":"ye","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1_2"},{"key":"ref16","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"achiam","year":"2016","journal-title":"Proc Deep RL Workshop Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"4424","article-title":"Distributional reinforcement learning for efficient exploration","author":"mavrin","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref19","first-page":"1","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref28","volume":"2","author":"bertsekas","year":"2011","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref4","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref27","first-page":"1","article-title":"Recurrent experience replay in distributed reinforcement learning","author":"kapturowski","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref3"},{"key":"ref6","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp Ser"},{"key":"ref29","first-page":"6190","article-title":"Fully parameterized quantile function for distributional reinforcement learning","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref8","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Art Int"},{"key":"ref7","article-title":"On improving deep reinforcement learning for POMDPs","author":"zhu","year":"2017","journal-title":"arXiv 1704 07978"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"jaksch","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Proc Deep Learning Workshop NIPS"},{"key":"ref20","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref22","first-page":"2721","article-title":"Count-based exploration with neural density models","volume":"70","author":"ostrovski","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref21","first-page":"1","article-title":"Contingency-aware exploration in reinforcement learning","author":"choi","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref42","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"arXiv 1912 06680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref23","first-page":"1","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref41","first-page":"1","article-title":"Model-based reinforcement learning for Atari","author":"kaiser","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref26","article-title":"Deep attention recurrent Q-network","author":"sorkin","year":"2015","journal-title":"arXiv 1512 01693"},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09615161.pdf?arnumber=9615161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T20:56:37Z","timestamp":1646686597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9615161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3128558","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}