# A Meta Reinforcement Learning Approach to Goals-Based Wealth Management

arXiv: https://arxiv.org/abs/2605.02300 · HTML: https://mlsanity.com/paper/2605.02300/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 20 of its 79 references that are in the map.
- First posted on arXiv 4 May 2026.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020)
- [Meta-Reinforcement Learning of Structured Exploration Strategies](https://mlsanity.com/paper/1802.07245/) (2018)
- [A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem](https://mlsanity.com/paper/1706.10059/) (2017)
- [Recent Advances in Reinforcement Learning in Finance](https://mlsanity.com/paper/2112.04553/) (2021)
- [Meta reinforcement learning as task inference](https://mlsanity.com/paper/1905.06424/) (2019)
- [Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm](https://mlsanity.com/paper/1710.11622/) (2017)
- [Model-Based Offline Meta-Reinforcement Learning with Regularization](https://mlsanity.com/paper/2202.02929/) (2022)
- [G-Learner and GIRL: Goal Based Wealth Management with Reinforcement Learning](https://mlsanity.com/paper/2002.10990/) (2020)
- [Distributional Offline Continuous-Time Reinforcement Learning with Neural Physics-Informed PDEs (SciPhy RL for DOCTR-L)](https://mlsanity.com/paper/2104.01040/) (2021)
- [Embracing advanced AI/ML to help investors achieve success: Vanguard Reinforcement Learning for Financial Goal Planning](https://mlsanity.com/paper/2110.12003/) (2021)
- [Optimal Execution Using Reinforcement Learning](https://mlsanity.com/paper/2306.17178/) (2023)

## Abstract (arXiv)

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.