Deep Reinforcement Learning in Agent Based Financial Market Simulation
Open Access
- 11 April 2020
- journal article
- research article
- Published by MDPI AG in Journal of Risk and Financial Management
- Vol. 13 (4) , 71
Abstract
Prediction of financial market data with deep learning models has achieved some level of recent success. However, historical financial data suffer from an unknowable state space, limited observations, and the inability to model the impact of your own actions on the market can often be prohibitive when trying to find investment strategies using deep reinforcement learning. One way to overcome these limitations is to augment real market data with agent based artificial market simulation. Artificial market simulations designed to reproduce realistic market features may be used to create unobserved market states, to model the impact of your own investment actions on the market itself, and train models with as much data as necessary. In this study we propose a framework for training deep reinforcement learning models in agent based artificial price-order-book simulations that yield non-trivial policies under diverse conditions with market impact. Our simulations confirm that the proposed deep reinforcement learning model with unique task-specific reward function was able to learn a robust investment strategy with an attractive risk-return profile.Keywords
This publication has 55 references indexed in Scilit:
- Zero intelligence in economics and financeThe Knowledge Engineering Review, 2012
- The Market Impact of Relative Agency Activity in the Sovereign Ratings MarketJournal of Business Finance & Accounting, 2010
- Agent-based models of financial marketsReports on Progress in Physics, 2007
- On the maximum drawdown of a Brownian motionJournal of Applied Probability, 2004
- A simulation analysis of the microstructure of double auction markets*Quantitative Finance, 2002
- Complexity and the EconomyScience, 1999
- Negotiation and cooperation in multi-agent environmentsArtificial Intelligence, 1997
- Detrending, stylized facts and the business cycleJournal of Applied Econometrics, 1993
- Common risk factors in the returns on stocks and bondsJournal of Financial Economics, 1993
- Conditional Heteroskedasticity in Asset Returns: A New ApproachEconometrica, 1991