{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T05:34:31Z","timestamp":1776404071978,"version":"3.51.2"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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":["61976215"],"award-info":[{"award-number":["61976215"]}],"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":["61772532"],"award-info":[{"award-number":["61772532"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tcyb.2021.3051456","type":"journal-article","created":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T21:05:51Z","timestamp":1615496751000},"page":"9428-9438","source":"Crossref","is-referenced-by-count":53,"title":["Authentic Boundary Proximal Policy Optimization"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China"}]},{"given":"Longyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2931946"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3023127"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3023033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8441797"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2783439"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2881359"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2477810"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2886735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921057"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927227"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref17","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"48","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref19","volume-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref21","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in Neural Information Processing Systems","author":"Sutton","year":"2000"},{"key":"ref22","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref23","author":"Chen","year":"2018","journal-title":"An adaptive clipping approach for proximal policy optimization"},{"key":"ref24","volume-title":"Truly proximal policy optimization","author":"Wang","year":"2019"},{"key":"ref25","volume-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00206"},{"key":"ref27","volume-title":"Policy optimization with penalized point probability distance: an alternative to proximal policy optimization","author":"Chu","year":"2018"},{"key":"ref28","volume-title":"ProMP: Proximal meta-policy search","author":"Rothfuss","year":"2018"},{"key":"ref29","volume-title":"Some considerations on learning to explore via meta-reinforcement learning","author":"Stadie","year":"2018"},{"key":"ref30","volume-title":"Optimistic proximal policy optimization","author":"Imagawa","year":"2019"},{"key":"ref31","volume-title":"Trust region-guided proximal policy optimization","author":"Wang","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231618"},{"key":"ref33","volume-title":"Proximal policy optimization and its dynamic version for sequence generation","author":"Tuan","year":"2018"},{"key":"ref34","volume-title":"A closer look at deep policy gradients","author":"Ilyas","year":"2018"},{"key":"ref35","volume-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","author":"Engstrom","year":"2020"},{"key":"ref36","volume-title":"A closer look at deep policy gradients","author":"Ilyas","year":"2018"},{"key":"ref37","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","volume":"2","author":"Kakade"},{"key":"ref38","volume-title":"Information Theory and Statistics","author":"Kullback","year":"1968"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9861400\/09376693.pdf?arnumber=9376693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:14:38Z","timestamp":1704845678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":38,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2021.3051456","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}