{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T04:13:06Z","timestamp":1792901586773,"version":"4.5.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4182056"],"award-info":[{"award-number":["4182056"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002888","name":"Joint Building Program of the Beijing Municipal Education Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002888","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1109\/tnnls.2019.2959129","type":"journal-article","created":{"date-parts":[[2020,1,14]],"date-time":"2020-01-14T22:37:47Z","timestamp":1579041467000},"page":"4933-4945","source":"Crossref","is-referenced-by-count":79,"title":["Reducing Estimation Bias via Triplet-Average Deep Deterministic Policy Gradient"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4938-5813","authenticated-orcid":false,"given":"Dongming","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1613-9288","authenticated-orcid":false,"given":"Xingping","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-3082","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4584-3453","authenticated-orcid":false,"given":"Steven C. H.","family":"Hoi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2936503"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref33","first-page":"1","article-title":"Deterministic implementations for reproducibility in deep reinforcement learning","author":"nagarajan","year":"2019","journal-title":"Proc 23rd AAAI Conf Artif Intell"},{"key":"ref32","first-page":"1","article-title":"Smoothed action value functions for learning Gaussian policies","author":"nachum","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref30","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref35","first-page":"1","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref34","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"popov","year":"2017","journal-title":"arXiv 1704 03073"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614994"},{"key":"ref27","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref29","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","first-page":"1","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Proc 22nd AAAI Conf Artif Intell"},{"key":"ref21","first-page":"1","article-title":"Deep recurrent q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp"},{"key":"ref24","first-page":"1","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","first-page":"1","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Proc 22nd AAAI Conf Artif Intell"},{"key":"ref26","first-page":"1188","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"khadka","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","first-page":"1","article-title":"Collaborative evolutionary reinforcement learning","author":"khadka","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","first-page":"1","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref51","first-page":"1","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/483"},{"key":"ref10","first-page":"1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","article-title":"How many random seeds? Statistical power analysis in deep reinforcement learning experiments","author":"colas","year":"2018","journal-title":"arXiv 1806 08295"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956703"},{"key":"ref13","first-page":"1","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","article-title":"Taming the noise in reinforcement learning via soft updates","author":"fox","year":"2015","journal-title":"arXiv 1512 08562"},{"key":"ref15","first-page":"1","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"1","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref18","first-page":"1","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2898567"},{"key":"ref4","first-page":"1","article-title":"Designing neural network architectures using reinforcement learning","author":"baker","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","first-page":"1","article-title":"Mean actor critic","volume":"1050","author":"asadi","year":"2017","journal-title":"Stat"},{"key":"ref6","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":"ref5","first-page":"1","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref7","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"},{"key":"ref49","author":"van hasselt","year":"2011","journal-title":"Insights in reinforcement learning"},{"key":"ref9","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840724"},{"key":"ref45","first-page":"1","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proc Connectionist Models Summer School"},{"key":"ref48","first-page":"1","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 20th AAAI Conf Artif Intell"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2921454"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref41","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9244673\/08957368.pdf?arnumber=8957368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:56Z","timestamp":1651079996000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8957368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":52,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2959129","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11]]}}}