Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-22850| Publication type: | Working paper – expertise – study |
| Title: | Deep reinforcement learning on a multi-asset environment for trading |
| Authors: | Hirsa, Ali Osterrieder, Jörg Hadji Misheva, Branka Posth, Jan-Alexander |
| et. al: | No |
| DOI: | 10.21256/zhaw-22850 |
| Extent: | 18 |
| Issue Date: | 2021 |
| Publisher / Ed. Institution: | arXiv |
| Other identifiers: | arXiv:2106.08437v1 |
| Language: | English |
| Subjects: | Deep reinforcement learning; Deep Q-network; Financial trading; Future |
| Subject (DDC): | 006: Special computer methods 332.6: Investment |
| Abstract: | Financial trading has been widely analyzed for decades with market participants and academics always looking for advanced methods to improve trading performance. Deep reinforcement learning (DRL), a recently reinvigorated method with significant success in multiple domains, still has to show its benefit in the financial markets. We use a deep Q-network (DQN) to design long-short trading strategies for futures contracts. The state space consists of volatility-normalized daily returns, with buying or selling being the reinforcement learning action and the total reward defined as the cumulative profits from our actions. Our trading strategy is trained and tested both on real and simulated price series and we compare the results with an index benchmark. We analyze how training based on a combination of artificial data and actual price series can be successfully deployed in real markets. The trained reinforcement learning agent is applied to trading the E-mini S&P 500 continuous futures contract. Our results in this study are preliminary and need further improvement. |
| URI: | https://arxiv.org/abs/2106.08437 https://digitalcollection.zhaw.ch/handle/11475/22850 |
| License (according to publishing contract): | CC BY-NC-ND 4.0: Attribution - Non commercial - No derivatives 4.0 International |
| Departement: | School of Engineering School of Management and Law |
| Organisational Unit: | Institute of Data Analysis and Process Design (IDP) Institute of Wealth & Asset Management (IWA) |
| Appears in collections: | Publikationen School of Management and Law |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2021_Hirsa-etal_Deep-reinforcement-learning.pdf | 1.04 MB | Adobe PDF |  View/Open |
Show full item record
Hirsa, A., Osterrieder, J., Hadji Misheva, B., & Posth, J.-A. (2021). Deep reinforcement learning on a multi-asset environment for trading. arXiv. https://doi.org/10.21256/zhaw-22850
Hirsa, A. et al. (2021) Deep reinforcement learning on a multi-asset environment for trading. arXiv. Available at: https://doi.org/10.21256/zhaw-22850.
A. Hirsa, J. Osterrieder, B. Hadji Misheva, and J.-A. Posth, “Deep reinforcement learning on a multi-asset environment for trading,” arXiv, 2021. doi: 10.21256/zhaw-22850.
HIRSA, Ali, Jörg OSTERRIEDER, Branka HADJI MISHEVA und Jan-Alexander POSTH, 2021. Deep reinforcement learning on a multi-asset environment for trading [online]. arXiv. Verfügbar unter: https://arxiv.org/abs/2106.08437
Hirsa, Ali, Jörg Osterrieder, Branka Hadji Misheva, and Jan-Alexander Posth. 2021. “Deep Reinforcement Learning on a Multi-Asset Environment for Trading.” arXiv. https://doi.org/10.21256/zhaw-22850.
Hirsa, Ali, et al. Deep Reinforcement Learning on a Multi-Asset Environment for Trading. arXiv, 2021, https://doi.org/10.21256/zhaw-22850.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.