{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T14:26:36Z","timestamp":1781360796154,"version":"3.54.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772532"],"award-info":[{"award-number":["61772532"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61751202"],"award-info":[{"award-number":["61751202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572540"],"award-info":[{"award-number":["61572540"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1813203"],"award-info":[{"award-number":["U1813203"]}],"id":[{"id":"10.13039\/501100001809","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":[[2020,6]]},"DOI":"10.1109\/tnnls.2019.2927227","type":"journal-article","created":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T19:53:11Z","timestamp":1565121191000},"page":"1820-1830","source":"Crossref","is-referenced-by-count":61,"title":["Approximate Policy-Based Accelerated Deep Reinforcement Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8849-5228","authenticated-orcid":false,"given":"Aiping","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"560","article-title":"Error bounds for approximate policy iteration","author":"munos","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref33","first-page":"2939","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref32","first-page":"4135","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref31","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref36","first-page":"2411","article-title":"Speedy Q-learning","author":"ghavamzadeh","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44581-1_39"},{"key":"ref34","first-page":"240","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280949"},{"key":"ref40","first-page":"568","article-title":"Error propagation for approximate policy and value iteration","author":"farahmand","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885530"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885374"},{"key":"ref13","first-page":"2850","article-title":"Asynchronous methods for deep reinforcement learning","volume":"4","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04182-3_25"},{"key":"ref15","article-title":"GA3C: GPU-based A3C for deep reinforcement learning","author":"babaeizadeh","year":"2016","journal-title":"arXiv 1611 06256"},{"key":"ref16","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2016","journal-title":"arXiv 1611 05397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CANDAR.2017.27"},{"key":"ref18","article-title":"Accelerated methods for deep reinforcement learning","author":"stooke","year":"2018","journal-title":"arXiv 1803 02811"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4236\/ica.2016.74012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500630"},{"key":"ref27","first-page":"2613","article-title":"Double Q-learning","author":"van hasselt","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2614675"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2861945"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2712561"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2017.7978240"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CCAA.2017.8229841"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2832025"},{"key":"ref9","first-page":"14","article-title":"High-level representations for game-tree search in RTS games","author":"uriarte","year":"2014","journal-title":"Proc Artif Intell Interact Digital Entert Conf"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2892151"},{"key":"ref20","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2764499"},{"key":"ref21","first-page":"8686","article-title":"Learning to explore with meta-policy gradient","volume":"12","author":"xu","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref24","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"arXiv 1803 00933"},{"key":"ref41","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":"ref23","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790981"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00039"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9106620\/08789695.pdf?arnumber=8789695","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\/8789695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":41,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2927227","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}