{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:23:08Z","timestamp":1780672988596,"version":"3.54.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2017R1D1A1B04036354"],"award-info":[{"award-number":["NRF-2017R1D1A1B04036354"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2854283","type":"journal-article","created":{"date-parts":[[2018,7,27]],"date-time":"2018-07-27T18:54:26Z","timestamp":1532717666000},"page":"49089-49102","source":"Crossref","is-referenced-by-count":53,"title":["A Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1345-2650","authenticated-orcid":false,"given":"Tuyen P.","family":"Le","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"TaeChoong","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Automated discovery of options in reinforcement learning","author":"stolle","year":"2004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5772\/13214"},{"key":"ref33","author":"vezhnevets","year":"2017","journal-title":"Feudal networks for hierarchical reinforcement learning"},{"key":"ref32","author":"lee","year":"2017","journal-title":"Micro-objective learning Accelerating deep reinforcement learning through the discovery of continuous subgoals"},{"key":"ref31","author":"fox","year":"2017","journal-title":"Multi-level discovery of deep options"},{"key":"ref30","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc AAAI"},{"key":"ref37","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"1993","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","author":"arulkumaran","year":"2016","journal-title":"Classifying options for deep reinforcement learning"},{"key":"ref34","author":"durugkar","year":"2016","journal-title":"Deep reinforcement learning with macro-actions"},{"key":"ref60","author":"abadi","year":"2015","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref62","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref61","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-015-0742-2"},{"key":"ref29","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":"ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref20","author":"sukhbaatar","year":"2015","journal-title":"MazeBase A sandbox for learning from games"},{"key":"ref22","article-title":"Hierarchical control and learning for Markov decision processes","author":"parr","year":"1998"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref23","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"1998","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"3613","article-title":"Hierarchical Monte-Carlo planning","author":"vien","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0565-6"},{"key":"ref50","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref51","first-page":"2140","article-title":"Playing FPS games with deep reinforcement learning","author":"lample","year":"2017","journal-title":"Proc AAAI"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref58","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","author":"mohamed","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref55","first-page":"112","article-title":"Intrinsically motivated learning of hierarchical collections of skills","author":"barto","year":"2004","journal-title":"Proc 3rd Int Conf Develop Learn"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.21236\/ADA440079","article-title":"Intrinsically motivated reinforcement learning: A promising framework for developmental robot learning","author":"stout","year":"2005"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1999.1020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref40","first-page":"3x","article-title":"A survey of POMDP solution techniques","volume":"2","author":"murphy","year":"2000"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1147\/JRD.2012.2188931","article-title":"Simulation, learning, and optimization techniques in Watson’s game strategies","volume":"56","author":"tesauro","year":"2012","journal-title":"IBM J Res Develop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2379-3_11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2003.821457"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"ref16","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.2.271"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.613"},{"key":"ref19","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref6","first-page":"690","article-title":"Stock price prediction using reinforcement learning","volume":"1","author":"lee","year":"2001","journal-title":"Proc IEEE Int Symp Ind Electron (ISIE)"},{"key":"ref5","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref49","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref46","first-page":"5","article-title":"Deep reinforcement learning with double Q-learning","volume":"2","author":"van hasselt","year":"2016","journal-title":"Proc AAAI"},{"key":"ref45","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref48","author":"schaul","year":"2015","journal-title":"Prioritized experience replay"},{"key":"ref47","author":"wang","year":"2015","journal-title":"Dueling network architectures for deep reinforcement learning"},{"key":"ref42","article-title":"Deep reinforcement learning with POMDPs","author":"egorov","year":"2015"},{"key":"ref41","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1287\/opre.24.2.348"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08421749.pdf?arnumber=8421749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:40Z","timestamp":1642004140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8421749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2854283","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}