Enhancing Portfolio Optimisation with Deep Reinforcement Learning: A Comparative Analysis

The aim of this paper is to understand and analyse how Portfolio Optimisation is enhanced while utilising Deep Reinforcement Learning (DRL) versus while using traditional optimisation methods. One of the objectives is also to focus on how DRL algorithms can navigate through the limitations of the traditional portfolio optimisation approach. The comparing of the two models will help gain a better understanding of the performance of the two models. This would also lead us to better insights on the potential advantages and limitations of DRL while it returns risk-adjusted returns for the portfolio.