A Comparison among Reinforcement Learning Algorithms in Financial Trading Systems

36 Pages Posted: 23 Jan 2020

See all articles by Marco Corazza

Marco Corazza

Ca Foscari University of Venice - Dipartimento di Economia

Giovanni Fasano

Ca Foscari University of Venice - Department of Management

Riccardo Gusso

Independent

Raffaele Pesenti

Ca Foscari University of Venice - Department of Management

Date Written: November 20, 2019

Abstract

In this work we analyze and implement different Reinforcement Learning (RL) algorithms in financial trading system applications. RL-based algorithms applied to financial systems aim to find an optimal policy, that is an optimal mapping between the variables describing the state of the system and the actions available to an agent, by interacting with the system itself in order to maximize a cumulative return. In this contribution we compare the results obtained considering different on-policy (SARSA) and off-policy (Q-Learning, Greedy-GQ) RL algorithms applied to daily trading in the Italian stock market. We consider both computational issues related to the implementation of the algorithms, and issues originating from practical application to real stock markets, in an effort to improve previous results while keeping a simple and understandable structure of the used models.

Keywords: Reinforcement Learning, SARSA, Q-Learning, Greedy-GQ, Financial Trading System, Italian FTSE Mib Stock Market

JEL Classification: C53, C54, E37, G17

Suggested Citation

Corazza, Marco and Fasano, Giovanni and Gusso, Riccardo and Pesenti, Raffaele, A Comparison among Reinforcement Learning Algorithms in Financial Trading Systems (November 20, 2019). University Ca' Foscari of Venice, Dept. of Economics Research Paper Series No. No. 33/WP/2019 . Available at SSRN: https://ssrn.com/abstract=3522712 or http://dx.doi.org/10.2139/ssrn.3522712

Marco Corazza

Ca Foscari University of Venice - Dipartimento di Economia ( email )

Cannaregio 873
Venice, 30121
Italy

Giovanni Fasano

Ca Foscari University of Venice - Department of Management ( email )

San Giobbe, Cannaregio 873
Venice, 30121
Italy

Riccardo Gusso (Contact Author)

Independent ( email )

No Address Available

Raffaele Pesenti

Ca Foscari University of Venice - Department of Management ( email )

San Giobbe, Cannaregio 873
Venice, 30121
Italy

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
44
Abstract Views
150
PlumX Metrics