Abstract
In this paper we present a deep reinforcement learning-based methodology for computing optimized trading policies. During the first stage of the methodology, we employ Gated Recurrent Units (GRUs) to predict the immediate future behaviour of the time series that describe the temporal dynamics of the value of a set of assets. Then, we employ a Deep Q-Learning Architecture to compute optimized trading policies that describe, at every point in time, which assets have to be bought and which have to be sold in order to maximize profit. Our experimental results, which are based on trading cryptocurrencies, show that the proposed algorithm effectively computes trading policies that achieve incremental profits from an initial budget.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
More than 1,000 cryptocurrencies have already failed - here’s what will affect successes in the future. https://finance.yahoo.com/news/more-1-000-cryptocurrencies-already-144541916.html. Accessed 03 Jun 2020
Crypto payments processor coinpayments partners with shopify. https://ibsintelligence.com/ibs-journal/ibs-news/crypto-payments-processor-coinpayments-partners-with-shopify/. Accessed 03 Jun 2020
Lee, J.W., Kim, S.D., Lee, J.: An intelligent stock trading system based on reinforcement learning. IEICE Trans. Inf. Syst. 86(20), 296–305 (2003)
Lee, J.W., Park, J., Jangmin, O., Lee, J., Hong, E.: A multiagent approach to \(q\)-learning for daily stock trading. IEEE Trans. Syst. Man Cybern. Part A Syst. Hum. 37(6), 864–877 (2007)
Dempster, M.A.H., Payne, T.W., Romahi, Y., Thompson, G.W.P.: Computational learning techniques for intraday FX trading using popular technical indicators. IEEE Trans. Neural Netw. 12(4), 744–754 (2001)
Chen, Y., Mabu, S., Hirasawa, K., Hu, J.: Trading rules on stock markets using genetic network programming with sarsa learning. In: Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation, GECCO 2007, New York, NY, USA, p. 1503. Association for Computing Machinery (2007)
Moody, J., Saffell, M.: Learning to trade via direct reinforcement. IEEE Trans. Neural Netw. 12(4), 875–889 (2001)
Moody, J., Wu, L.: Optimization of trading systems and portfolios. In: Proceedings of the IEEE/IAFE 1997 Computational Intelligence for Financial Engineering (CIFEr), pp. 300–307 (1997)
Dempster, M.A.H., Leemans, V.: An automated FX trading system using adaptive reinforcement learning. Expert Syst. Appl. 30(3), 543–552 (2006). Intelligent Information Systems for Financial Engineering
Gorse, D.: Application of stochastic recurrent reinforcement learning to index trading. In: ESANN 2011: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (2011)
Zhang, J., Maringer, D.: Using a genetic algorithm to improve recurrent reinforcement learning for equity trading. Comput. Econ. 47(4), 551–567 (2016). https://doi.org/10.1007/s10614-015-9490-y
Jangmin, O., Lee, J., Lee, J.W., Zhang, B.T.: Adaptive stock trading with dynamic asset allocation using reinforcement learning. Inf. Sci. 176(15), 2121–2147 (2006)
Deng, Y., Bao, F., Kong, Y., Ren, Z., Dai, Q.: Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans. Neural Netw. Learn. Syst. 28(3), 653–664 (2017)
David, W.L.: Agent inspired trading using recurrent reinforcement learning and LSTM neural networks (2017)
Mnih, V.: Playing atari with deep reinforcement learning. 2013. cite arxiv:1312.5602Comment. NIPS Deep Learning Workshop (2013)
Get started with bitcoin. https://bitcoin.org/en/. Accessed: 2020–06-04
What is litecoin? https://litecoin.org/. Accessed 04 Jun 2020
What is ethereum? https://ethereum.org/what-is-ethereum/. Accessed 04 Jun 2020
Lin, L.J.: Reinforcement learning for robots using neural networks. Ph.D. thesis, USA (1992)
Liu, R., Zou, J: The effects of memory replay in reinforcement learning, October 2017
Bertsekas, D.P.: Reinforcement learning and optimal control. In: Bertsekas, D., Nedić, A., Ozdaglar, A.E. (eds.) Athena Scientific Optimization and Computation Series. Athena Scientific, Belmont (2019)
Top 100 cryptocurrencies by market capitalization. https://coinmarketcap.com/. Accessed 04 Jun 2020
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Corona-Bermudez, U., Menchaca-Mendez, R., Menchaca-Mendez, R. (2020). On the Computation of Optimized Trading Policies Using Deep Reinforcement Learning. In: Mata-Rivera, M.F., Zagal-Flores, R., Barria-Huidobro, C. (eds) Telematics and Computing. WITCOM 2020. Communications in Computer and Information Science, vol 1280. Springer, Cham. https://doi.org/10.1007/978-3-030-62554-2_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-62554-2_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62553-5
Online ISBN: 978-3-030-62554-2
eBook Packages: Computer ScienceComputer Science (R0)