Abstract
Researchers have reported success in developing autonomous trade execution systems based on Deep Reinforcement Learning (DRL) techniques aiming to minimize the execution costs. However, they all back-test the trade execution policies on historical datasets. One of the biggest drawbacks of back-testing on historical datasets is that it cannot account for the permanent market impacts caused by interactions among various trading agents and real-world factors such as network latency and computational delays.
In this article, we investigate an agent-based market simulator as a back-testing tool. More specifically, we design agents which use the trade execution policies learned by two previously proposed Deep Reinforcement Learning algorithms, a modified Deep-Q Network (DQN) and Proximal Policy Optimization with Long-Short Term Memory networks (PPO LSTM), to execute trades and interact with each other in the market simulator.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For example, the differences of immediate rewards between different time steps, indicators to represent various market scenarios (i.e., regime shift, trends in price changes, etc.).
- 2.
TWAP represents the volume projections of the TWAP strategy in one step.
- 3.
Implementation Shortfall = (arrival price − executed price) \(\times \) traded volume.
References
Byrd, D.: Explaining agent-based financial market simulation. arXiv preprint arXiv:1909.11650 (2019)
Byrd, D., et al.: ABIDES: towards high-fidelity market simulation for AI research. arXiv preprint arXiv:1904.12066 (2019)
Chakraborty, T., Kearns, M.: Market making and mean reversion. In: Proceedings of the 12th ACM Conference on Electronic Commerce, San Jose, CA, USA (2011)
Hendricks, D., Wilcox, D.: A reinforcement learning extension to the Almgren-Chriss framework for optimal trade execution. In: Proceedings of the IEEE Conference on Computational Intelligence for Financial Economics and Engineering, London, UK, pp. 457–464 (2014)
Lin, S., Beling, P.-A.: Optimal liquidation with deep reinforcement learning. In: Proceedings of the 33rd Conference on Neural Information Processing Systems, Deep Reinforcement Learning Workshop, Vancouver, Canada (2019)
Lin, S., Beling, P.-A.: An end-to-end optimal trade execution framework based on proximal policy optimization. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence (2020)
Lin, S., Beling, P.A.: A deep reinforcement learning framework for optimal trade execution. In: Dong, Y., Ifrim, G., Mladenić, D., Saunders, C., Van Hoecke, S. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12461, pp. 223–240. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67670-4_14
Lin, S., Beling, P.A.: Investigating the robustness and generalizability of deep reinforcement learning based optimal trade execution systems. In: Arai, K. (ed.) Intelligent Computing. LNNS, vol. 284, pp. 912–926. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-80126-7_64
Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)
Nevmyvaka, Y., et al.: Reinforcement learning for optimal trade execution. In: Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, pp. 673–68. Association for Computing Machinery (2006)
Ning, B., Ling, F.-H.-T., Jaimungal, S.: Double deep Q-learning for optimal execution. arXiv arXiv:1812.06600 (2018)
Schulman, J., et al.: Proximal policy optimization algorithms. arXiv:1811.08540v2 (2017)
Wah, E., et al.: Welfare effects of market making in continuous double auctions. J. Artif. Intell. Res. 59, 613–650 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, S., Beling, P.A. (2021). An Agent-Based Market Simulator for Back-Testing Deep Reinforcement Learning Based Trade Execution Strategies. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13110. Springer, Cham. https://doi.org/10.1007/978-3-030-92238-2_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-92238-2_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92237-5
Online ISBN: 978-3-030-92238-2
eBook Packages: Computer ScienceComputer Science (R0)