English

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

Artificial Intelligence 2024-03-26 v1

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.

Keywords

Cite

@article{arxiv.2403.16667,
  title  = {Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization},
  author = {Fernando Acero and Parisa Zehtabi and Nicolas Marchesotti and Michael Cashmore and Daniele Magazzeni and Manuela Veloso},
  journal= {arXiv preprint arXiv:2403.16667},
  year   = {2024}
}

Comments

Presented at the AAAI 2024 Workshop on AI in Finance for Social Impact

R2 v1 2026-06-28T15:32:33.995Z