Deep Reinforcement Learning (DRL) for Portfolio Allocation

Abstract

Deep reinforcement learning (DRL) has reached an unprecedent level on complex tasks like game solving (Go or StarCraft II), and autonomous driving. However, applications to real financial assets are still largely unexplored and it remains an open question whether DRL can reach super human level. In this ECML PKKDD demo, we showcase state-of-the-art DRL methods for selecting portfolios according to financial environment, with a final network concatenating three individual networks using layers of convolutions to reduce network's complexity.

The multi entries of our network enables capturing dependencies from common financial indicators features like risk aversion, citigroup index surprise, portfolio specific features and previous portfolio allocations. Results on test set show this approach can overperform traditional portfolio optimization methods.

Keywords: Deep Reinforcement Learning, Portfolio Selection

JEL Classification: G11