{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T03:34:18Z","timestamp":1775705658674,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Thai Government through DPST scholarship"},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L016796\/1"],"award-info":[{"award-number":["EP\/L016796\/1"]}],"id":[{"id":"10.13039\/501100000266","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":[[2019,11]]},"DOI":"10.1109\/tnnls.2019.2891792","type":"journal-article","created":{"date-parts":[[2019,1,29]],"date-time":"2019-01-29T20:05:57Z","timestamp":1548792357000},"page":"3409-3418","source":"Crossref","is-referenced-by-count":68,"title":["Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7721-7564","authenticated-orcid":false,"given":"Nat","family":"Dilokthanakul","sequence":"first","affiliation":[]},{"given":"Christos","family":"Kaplanis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2748-7977","authenticated-orcid":false,"given":"Nick","family":"Pawlowski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5984-2964","authenticated-orcid":false,"given":"Murray","family":"Shanahan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref33","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref31","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref37","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","author":"wang","year":"2016","journal-title":"Learning to reinforcement learn"},{"key":"ref34","author":"forestier","year":"2017","journal-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning"},{"key":"ref10","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"1998","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref12","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":"ref13","article-title":"FeUdal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","author":"bengio","year":"2017","journal-title":"Independently controllable features"},{"key":"ref15","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":"ref16","first-page":"1109","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554676"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref4","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2785233"},{"key":"ref3","author":"nagabandi","year":"2017","journal-title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning"},{"key":"ref6","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":"ref29","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref5","first-page":"113","article-title":"Intrinsic motivation for reinforcement learning systems","author":"barto","year":"2005","journal-title":"Proc Yale Workshop Adaptive Learning Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref2","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":"ref9","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"konidaris","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref22","first-page":"1","article-title":"Variational intrinsic control","author":"gregor","year":"2017","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref21","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":"ref24","author":"mirowski","year":"2016","journal-title":"Learning to navigate in complex environments"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref25","author":"shelhamer","year":"2016","journal-title":"Loss is its own reward Self-supervision for reinforcement learning"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8886738\/08629360.pdf?arnumber=8629360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:14:40Z","timestamp":1657746880000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8629360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":38,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2891792","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}