Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management

TL;DR

This paper introduces a regularization method for reinforcement learning in asset management that incorporates intrinsic preferences, enabling personalized strategies that are interpretable and maintain high returns.

Contribution

The paper presents a novel regularization approach that embeds intrinsic affinity into RL policies, allowing for personalized and interpretable asset management strategies.

Findings

RL agents can be trained to follow personalized policies based on intrinsic affinities.

The method achieves high returns while respecting individual preferences.

Strategies are more interpretable due to the intrinsic affinity regularization.

Abstract

The common purpose of applying reinforcement learning (RL) to asset management is the maximization of profit. The extrinsic reward function used to learn an optimal strategy typically does not take into account any other preferences or constraints. We have developed a regularization method that ensures that strategies have global intrinsic affinities, i.e., different personalities may have preferences for certain assets which may change over time. We capitalize on these intrinsic policy affinities to make our RL model inherently interpretable. We demonstrate how RL agents can be trained to orchestrate such individual policies for particular personality profiles and still achieve high returns.