Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization

TL;DR

This paper explores the application of deep reinforcement learning to responsible portfolio optimization by integrating ESG objectives, comparing its performance with traditional mean-variance methods, and demonstrating competitive results.

Contribution

It introduces a deep reinforcement learning framework that incorporates ESG considerations into portfolio optimization, advancing responsible investment strategies.

Findings

Deep reinforcement learning achieves competitive performance with mean-variance methods.

Incorporating ESG objectives into RL policies enhances responsible investment.

Results are consistent across different utility functions.

Abstract

Portfolio optimization involves determining the optimal allocation of portfolio assets in order to maximize a given investment objective. Traditionally, some form of mean-variance optimization is used with the aim of maximizing returns while minimizing risk, however, more recently, deep reinforcement learning formulations have been explored. Increasingly, investors have demonstrated an interest in incorporating ESG objectives when making investment decisions, and modifications to the classical mean-variance optimization framework have been developed. In this work, we study the use of deep reinforcement learning for responsible portfolio optimization, by incorporating ESG states and objectives, and provide comparisons against modified mean-variance approaches. Our results show that deep reinforcement learning policies can provide competitive performance against mean-variance approaches for responsible portfolio allocation across additive and multiplicative utility functions of financial and ESG responsibility objectives.