{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:40:02Z","timestamp":1755884402108,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP20220-0013, R-144-000-457-733 (A-0004550-00-00)"],"award-info":[{"award-number":["MOE-T2EP20220-0013, R-144-000-457-733 (A-0004550-00-00)"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,14]]},"DOI":"10.1145\/3677052.3698657","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:38:06Z","timestamp":1731566286000},"page":"686-694","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Navigating the Difficulty of Achieving Global Optimality under Variance-Induced Time Inconsistency"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7921-0175","authenticated-orcid":false,"given":"Jingxiang","family":"Tang","sequence":"first","affiliation":[{"name":"School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3705-3382","authenticated-orcid":false,"given":"Nixie S","family":"Lesmana","sequence":"additional","affiliation":[{"name":"School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore and Department of Physics, Faculty of Science, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7478-6961","authenticated-orcid":false,"given":"Chi Seng","family":"Pun","sequence":"additional","affiliation":[{"name":"School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2001.041"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00780-014-0234-y"},{"key":"e_1_3_2_1_3_1","volume-title":"Learning equilibrium mean-variance strategy. Available at SSRN 3770818 33, 4","author":"Dai Min","year":"2020","unstructured":"Min Dai, Yuchao Dong, and Yanwei Jia. 2020. Learning equilibrium mean-variance strategy. Available at SSRN 3770818 33, 4 (2020), 1166\u20131212."},{"volume-title":"Dynamic programming and markov processes","author":"Howard A","key":"e_1_3_2_1_4_1","unstructured":"Ronald\u00a0A Howard. 1960. Dynamic programming and markov processes.The MIT Press, Cambridge, Massachusetts."},{"key":"e_1_3_2_1_5_1","volume-title":"Convergence of one class of random search algorithms. Avtomat i Telemekh 8","author":"Katkovnik V\u00a0Ya","year":"1972","unstructured":"V\u00a0Ya Katkovnik and O\u00a0Yu Kul\u2019chitskii. 1972. Convergence of one class of random search algorithms. Avtomat i Telemekh 8 (1972), 81\u201387."},{"key":"e_1_3_2_1_6_1","volume-title":"Actor-Critic Algorithms for Risk-Sensitive MDPs. Advances in Neural Information Processing Systems 26 (02","author":"Mohammad Ghavamzadeh Prashanth","year":"2013","unstructured":"Prashanth L.A. and Mohammad Ghavamzadeh. 2013. Actor-Critic Algorithms for Risk-Sensitive MDPs. Advances in Neural Information Processing Systems 26 (02 2013)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3951936"},{"key":"e_1_3_2_1_8_1","volume-title":"Reinventing Policy Iteration under Time Inconsistency. Transactions on Machine Learning Research","author":"Lesmana S","year":"2022","unstructured":"Nixie\u00a0S Lesmana, Huangyuan Su, and Chi\u00a0Seng Pun. 2022. Reinventing Policy Iteration under Time Inconsistency. Transactions on Machine Learning Research (2022). https:\/\/openreview.net\/forum?id=bN2vWLTh0P"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9965.00100"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML\u201911)","author":"Mannor Shie","year":"2011","unstructured":"Shie Mannor and John\u00a0N. Tsitsiklis. 2011. Mean-Variance Optimization in Markov Decision Processes. In Proceedings of the 28th International Conference on International Conference on Machine Learning (ICML\u201911) (Bellevue, Washington, USA). Omnipress, Madison, WI, USA, 177\u2013184."},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman L","key":"e_1_3_2_1_11_1","unstructured":"Martin\u00a0L Puterman. 2014. Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons, New York."},{"key":"e_1_3_2_1_12_1","volume-title":"Risk-averse dynamic programming for Markov decision processes. Mathematical programming 125","author":"Ruszczy\u0144ski Andrzej","year":"2010","unstructured":"Andrzej Ruszczy\u0144ski. 2010. Risk-averse dynamic programming for Markov decision processes. Mathematical programming 125 (2010), 235\u2013261."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.2307\/3213832"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.119632"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.2307\/2295722"},{"key":"e_1_3_2_1_16_1","volume-title":"Policy gradient methods for reinforcement learning with function approximation. Advances in neural information processing systems 12","author":"Sutton S","year":"1999","unstructured":"Richard\u00a0S Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. Advances in neural information processing systems 12 (1999), 1057\u20131063."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042573.3042784"},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Learning the Variance of the Reward-To-Go","volume":"17","author":"Tamar Aviv","year":"2016","unstructured":"Aviv Tamar, Dotan\u00a0Di Castro, and Shie Mannor. 2016. Learning the Variance of the Reward-To-Go. Journal of Machine Learning Research 17, 13 (2016), 1\u201336. http:\/\/jmlr.org\/papers\/v17\/14-335.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_19_1","unstructured":"Aviv Tamar and Shie Mannor. 2013. Variance Adjusted Actor Critic Algorithms. arxiv:1310.3697\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1310.3697"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12281"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12281"},{"key":"e_1_3_2_1_22_1","volume-title":"Watkins and Peter Dayan","author":"H.","year":"1992","unstructured":"Christopher\u00a0J.C.H. Watkins and Peter Dayan. 1992. Q-learning. Machine learning 8, 3-4 (May 1992), 279\u2013292."}],"event":{"name":"ICAIF '24: 5th ACM International Conference on AI in Finance","acronym":"ICAIF '24","location":"Brooklyn NY USA"},"container-title":["Proceedings of the 5th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698657","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677052.3698657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:14:30Z","timestamp":1755882870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":22,"alternative-id":["10.1145\/3677052.3698657","10.1145\/3677052"],"URL":"https:\/\/doi.org\/10.1145\/3677052.3698657","relation":{},"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}