{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:53:01Z","timestamp":1775145181299,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003802","name":"General Research Funds established under the University Grant Committee of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["14200417"],"award-info":[{"award-number":["14200417"]}],"id":[{"id":"10.13039\/501100003802","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":[[2020,9]]},"DOI":"10.1109\/tnnls.2019.2942951","type":"journal-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T19:22:31Z","timestamp":1571685751000},"page":"3319-3333","source":"Crossref","is-referenced-by-count":21,"title":["AlphaSeq: Sequence Discovery With Deep Reinforcement Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6300-3175","authenticated-orcid":false,"given":"Yulin","family":"Shao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7055-6483","authenticated-orcid":false,"given":"Soung Chang","family":"Liew","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9454-4997","authenticated-orcid":false,"given":"Taotao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","author":"shao","year":"2018","journal-title":"AlphaSeq Sequence discovery with deep reinforcement learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref11","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017","journal-title":"arXiv 1701 07274"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1983.1056744"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"ref16","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"arXiv 1712 01815"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/9780470022962"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2639739"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/35.956124"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.1994.580182"},{"key":"ref4","author":"skolnik","year":"2008","journal-title":"Radar Handbook"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/461\/08991"},{"key":"ref3","volume":"122","author":"viterbi","year":"1995","journal-title":"CDMA Principles of Spread Spectrum Communication"},{"key":"ref6","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.1973.309769"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2801888"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref7","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ygeno.2015.11.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","year":"1964","journal-title":"The On-Line Encyclopedia of Integer Sequences"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1974.1055219"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053969"},{"key":"ref21","author":"shao","year":"2018","journal-title":"AlphaSeq Sequence discovery with deep reinforcement learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITWITWN.2007.4318030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2007.357142"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/11617983_4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056505"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9184294\/08877997.pdf?arnumber=8877997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:50Z","timestamp":1651079990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8877997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":30,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2942951","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9]]}}}