Abstract:Applying concepts related to zero-shot meta-learning and pre-training of foundation models, we develop a meta reinforcement learning approach (denoted MetaRL) that is pre-trained on thousands of goals-based wealth management (GBWM) problems. Each GBWM problem involves a multiple year scenario over which the investor looks to optimally choose an investment portfolio each year and choose to fulfill all, some, or none of the different financial goals that arise each year. These choices seek to maximize the expected total investor utility obtained from the fulfilled financial goals. By eliminating separate training and optimization for each new investor problem, the MetaRL model in inference mode produces near-optimal dynamic investment portfolio and goal-fulfilling strategies for a new GBWM problem within a few hundredths of a second. This delivers expected utilities that are, on average, 97.8% of the optimal expected utilities (determined via Dynamic Programming). These results are remarkably robust to capital market regime changes, even when training uses only one capital market regime. Further, the MetaRL approach can enable solving problems with larger state spaces where Dynamic Programming becomes computationally infeasible.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.02300 [cs.LG] |
| (or arXiv:2605.02300v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02300 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | The Journal of Finance and Data Science, Volume 12, 2026, 100186,ISSN 2405-9188 |
| Related DOI: | https://doi.org/10.1016/j.jfds.2026.100186
DOI(s) linking to related resources |
From: Harshad Khadilkar [view email]
[v1]
Mon, 4 May 2026 07:48:02 UTC (1,511 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。