{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T10:41:18Z","timestamp":1770288078959,"version":"3.49.0"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tnnls.2020.2980743","type":"journal-article","created":{"date-parts":[[2020,4,10]],"date-time":"2020-04-10T20:17:52Z","timestamp":1586549872000},"page":"1162-1176","source":"Crossref","is-referenced-by-count":28,"title":["A3C-GS: Adaptive Moment Gradient Sharing With Locks for Asynchronous Actor\u2013Critic Agents"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5321-377X","authenticated-orcid":false,"given":"Alfonso B.","family":"Labao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5260-4429","authenticated-orcid":false,"given":"Mygel Andrei M.","family":"Martija","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7140-1707","authenticated-orcid":false,"given":"Prospero C.","family":"Naval","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04179-3_58"},{"key":"ref11","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2016","journal-title":"arXiv 1611 01224"},{"key":"ref12","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref13","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref15","first-page":"1","article-title":"ViZDoom: DRQN with prioritized experience replay, double-Q learning and snapshot ensembling","author":"schulze","year":"2018","journal-title":"Proc SAI Intell Syst Conf"},{"key":"ref16","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-5127-0_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808203"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489747"},{"key":"ref6","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2884797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545231"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref2","first-page":"3846","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","author":"gu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref9","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2016","journal-title":"arXiv 1611 03673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref22","first-page":"2595","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume":"70","author":"bellemare","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9365681\/09063667.pdf?arnumber=9063667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:08Z","timestamp":1652194388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9063667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":22,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2980743","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}