{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:57:01Z","timestamp":1778702221981,"version":"3.51.4"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["2022-0-00984"],"award-info":[{"award-number":["2022-0-00984"]}]},{"DOI":"10.13039\/501100010418","name":"Development of Artificial Intelligence Technology for Personalized Plug-and-Play Explanation and Verification of Explanation","doi-asserted-by":"publisher","award":["2019-0-00079"],"award-info":[{"award-number":["2019-0-00079"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002642","name":"Artificial Intelligence Graduate School Program, Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","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":[[2024,1]]},"DOI":"10.1109\/tnnls.2022.3174642","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T20:33:30Z","timestamp":1653338010000},"page":"362-375","source":"Crossref","is-referenced-by-count":14,"title":["Uncertainty-Aware Portfolio Management With Risk-Sensitive Multiagent Network"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9958-2335","authenticated-orcid":false,"given":"Kidon","family":"Park","sequence":"first","affiliation":[{"name":"Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3149-2354","authenticated-orcid":false,"given":"Hong-Gyu","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3343-983X","authenticated-orcid":false,"given":"Tae-San","family":"Eom","sequence":"additional","affiliation":[{"name":"Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-4996","authenticated-orcid":false,"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1080.0986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.37.5.519"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1952.tb01525.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330647"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545666"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017940631555"},{"key":"ref8","article-title":"Mean-variance optimization in Markov decision processes","author":"Mannor","year":"2011","journal-title":"arXiv:1104.5601"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1257\/jep.15.4.143"},{"key":"ref10","first-page":"4393","article-title":"Deep one-class classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ruff"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref12","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0180944"},{"key":"ref14","article-title":"Enhancing stock movement prediction with adversarial training","author":"Feng","year":"2018","journal-title":"arXiv:1810.09936"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2705658"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2827952"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5462"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112891"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220113"},{"key":"ref20","article-title":"Risk-averse trust region optimization for reward-volatility reduction","author":"Bisi","year":"2019","journal-title":"arXiv:1912.03193"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422519"},{"key":"ref22","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dabney"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3905\/jpm.1994.409501"},{"issue":"1","key":"ref24","first-page":"40","article-title":"Calmar ratio: A smoother tool","volume":"20","author":"Young","year":"1991","journal-title":"Futures"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref26","article-title":"Weight uncertainty in neural networks","author":"Blundell","year":"2015","journal-title":"arXiv:1505.05424"},{"key":"ref27","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lakshminarayanan"},{"key":"ref28","volume-title":"The MNIST Database of Handwritten Digits","author":"LeCun","year":"1998"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref30","article-title":"Exploration in deep reinforcement learning: A comprehensive survey","author":"Yang","year":"2021","journal-title":"arXiv:2109.06668"},{"key":"ref31","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Osband"},{"key":"ref32","article-title":"UCB exploration via Q-ensembles","author":"Chen","year":"2017","journal-title":"arXiv:1706.01502"},{"key":"ref33","article-title":"Efficient exploration with double uncertain value networks","author":"Moerland","year":"2017","journal-title":"arXiv:1711.10789"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/376"},{"key":"ref35","article-title":"Information-directed exploration for deep reinforcement learning","author":"Nikolov","year":"2018","journal-title":"arXiv:1812.07544"},{"key":"ref36","first-page":"4424","article-title":"Distributional reinforcement learning for efficient exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mavrin"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102459"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref41","article-title":"Collaborative learning for deep neural networks","author":"Song","year":"2018","journal-title":"arXiv:1805.11761"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511560033"},{"key":"ref43","article-title":"A deep reinforcement learning framework for the financial portfolio management problem","author":"Jiang","year":"2017","journal-title":"arXiv:1706.10059"},{"key":"ref44","volume-title":"Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence","author":"Weiss","year":"1999"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-49470-7"},{"key":"ref46","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"arXiv:1706.02275"},{"key":"ref47","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref48","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref50","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref51","article-title":"A review of cooperative multi-agent deep reinforcement learning","author":"OroojlooyJadid","year":"2019","journal-title":"arXiv:1908.03963"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24251\/HICSS.2018.157"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref55","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster"},{"key":"ref56","article-title":"Multi-agent actor-critic with generative cooperative policy network","author":"Ryu","year":"2018","journal-title":"arXiv:1810.09206"},{"key":"ref57","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref58","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2995814"},{"key":"ref60","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"Foerster","year":"2016","journal-title":"arXiv:1605.06676"},{"key":"ref61","article-title":"Learning to play guess who? And inventing a grounded language as a consequence","author":"Jorge","year":"2016","journal-title":"arXiv:1611.03218"},{"key":"ref62","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"Kendall","year":"2017","journal-title":"arXiv:1703.04977"},{"issue":"10","key":"ref63","first-page":"99","article-title":"Maximum drawdown","volume":"17","author":"Magdon-Ismail","year":"2004","journal-title":"Risk Mag."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2011.11.003"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1111\/1540-6261.00580"},{"key":"ref66","article-title":"On-line portfolio selection with moving average reversion","author":"Li","year":"2012","journal-title":"arXiv:1206.4626"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2563433"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref70","first-page":"12060","article-title":"Pareto multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeuIPS)","volume":"32","author":"Lin"},{"key":"ref71","first-page":"6597","article-title":"Multi-task learning with user preferences: Gradient descent with controlled ascent in Pareto optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mahapatra"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10381493\/09779871.pdf?arnumber=9779871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:48:01Z","timestamp":1705020481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9779871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":71,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3174642","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}