{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T18:55:36Z","timestamp":1781376936031,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government [Ministry of Science and ICT (MSIT)] through the Development of 5G+ Intelligent Base-Station Software Modem","award":["2021-0-00165"],"award-info":[{"award-number":["2021-0-00165"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["2021R1A2C2095289"],"award-info":[{"award-number":["2021R1A2C2095289"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3494859","type":"journal-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:43:33Z","timestamp":1731350613000},"page":"166553-166563","source":"Crossref","is-referenced-by-count":6,"title":["Uncertainty-Aware Reinforcement Learning for Portfolio Optimization"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7415-3152","authenticated-orcid":false,"given":"Bayaraa","family":"Enkhsaikhan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Chungbuk National University, Cheongju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8444-2786","authenticated-orcid":false,"given":"Ohyun","family":"Jo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Chungbuk National University, Cheongju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2001.931880"},{"key":"ref2","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10562-9"},{"key":"ref4","article-title":"Quantifying epistemic uncertainty in deep learning","author":"Huang","year":"2021","journal-title":"arXiv:2110.12122"},{"key":"ref5","first-page":"9690","article-title":"Uncertainty estimation using a single deep deterministic neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"119","author":"Van Amersfoort"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref7","article-title":"Provably safe reinforcement learning: A theoretical and experimental comparison","author":"Krasowski","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9561"},{"key":"ref9","first-page":"32639","article-title":"Efficient risk-averse reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Greenberg"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1023\/A:1017940631555","article-title":"Risk-sensitive reinforcement learning","volume":"49","author":"Mihatsch","year":"1998","journal-title":"Mach. Learn."},{"issue":"4","key":"ref11","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/j.icte.2024.04.010","article-title":"Risk-averse reinforcement learning for portfolio optimization","volume":"10","author":"Enkhsaikhan","year":"2024","journal-title":"ICT Exp."},{"issue":"167","key":"ref12","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.2209"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0180944"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2014.6924100"},{"key":"ref16","article-title":"A deep reinforcement learning framework for the financial portfolio management problem","author":"Jiang","year":"2017","journal-title":"arXiv:1706.10059"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.1824207"},{"issue":"1","key":"ref19","first-page":"77","article-title":"Portfolio selection","volume":"7","author":"Markowitz","year":"1952","journal-title":"J. Finance"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref21","first-page":"20685","article-title":"Likelihood regret: An out-of-distribution detection score for variational auto-encoder","volume-title":"Proc. 34th Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref23","article-title":"Efficient exploration in binary and preferential Bayesian optimization","author":"Fauvel","year":"2021","journal-title":"arXiv:2110.09361"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref25","first-page":"1","article-title":"Variational autoencoder based anomaly detection using reconstruction probability","volume-title":"Proc. Special Lect. IE","author":"An"},{"key":"ref26","article-title":"WAIC, but why? Generative ensembles for robust anomaly detection","author":"Choi","year":"2019","journal-title":"arXiv:1810.01392"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.econmod.2022.106078"},{"key":"ref29","article-title":"Risk-averse offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Urp\u00ed"},{"key":"ref30","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref31","volume-title":"Technical Analysis From A To Z","author":"Achelis","year":"2013"},{"key":"ref32","volume-title":"Neural Networks for Financial Forecasting","author":"Gately","year":"1995"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref34","first-page":"1875","article-title":"Sample efficient actor-critic with experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118196","article-title":"Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection","volume":"209","author":"Yong","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2022.108529","article-title":"A prescriptive Dirichlet power allocation policy with deep reinforcement learning","volume":"224","author":"Tian","year":"2022","journal-title":"Rel. Eng. Syst. Saf."},{"key":"ref37","first-page":"954","article-title":"Do deep generative models know what they don\u2019t know?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nalisnick"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref40","first-page":"339","article-title":"Epistemic risk-sensitive reinforcement learning","volume-title":"Proc. Eur. Symp. Artif. Neural Netw. (ESANN), Comput. Intell. Mach. Learn.","author":"Eriksson"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10749817.pdf?arnumber=10749817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T14:36:09Z","timestamp":1732718169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10749817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3494859","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}