Policy Gradient with Expected Quadratic Utility Maximization: A New Mean-Variance Approach in Reinforcement Learning

Masahiro Kato, Kei Nakagawa

Keywords: mean-variance reinforcement learning, finance

Abstract: In real-world decision-making problems, risk management is critical. Among various risk management approaches, the mean-variance criterion is one of the most widely used in practice. In this paper, we suggest expected quadratic utility maximization (EQUM) as a new framework for policy gradient style reinforcement learning (RL) algorithms with mean-variance control. The quadratic utility function is a common objective of risk management in finance and economics. The proposed EQUM framework has several interpretations, such as reward-constrained variance minimization and regularization, as well as agent utility maximization. In addition, the computation of the EQUM framework is easier than that of existing mean-variance RL methods, which require double sampling. In experiments, we demonstrate the effectiveness of the proposed framework in benchmark setting of RL and financial data.

One-sentence Summary: Proposition of a expected quadratic utility maximization for mean-variance reinforcement learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=4H9F-LK5Q3