Resilience of Deep Q-Network (DQN) Agent in Mitigating Ethereum Trading Risks Under Bearish Market Conditions
DOI:
https://doi.org/10.24246/ijiteb.822026.28-34Keywords:
Deep Q-Network, Ethereum, Reinforcement Learning, Technical Indicators, Risk MitigationAbstract
The high volatility of cryptocurrency assets, particularly Ethereum, poses a significant challenge for investors during market downturns. Traditional passive strategies often lead to substantial capital erosion in bearish conditions. This study explores the application of Deep Reinforcement Learning (DRL) through the Deep Q-Network (DQN) algorithm to develop an adaptive trading agent. By integrating technical indicators—Relative Strength Index (RSI), Simple Moving Average (SMA), and Moving Average Convergence Divergence (MACD)—the proposed model aims to optimize decision-making processes. Experimental results using historical data from 2020 to 2026 demonstrate that while the market experienced a significant decline of 19.55%, the DQN agent successfully maintained capital stability with a marginal deviation of only -0.54%. This finding suggests that the DQN-based approach offers superior risk mitigation and capital preservation capabilities compared to conventional buy-and-hold strategies in volatile financial environments.Downloads
References
Abas, A., Ismail, M. A., Deep Reinforcement Learning for Cryptocurrency Trading: Practical Approach and Challenges, Journal of Financial Data Science 4 (1) (2022) 88–105.
Baur, D. G., Hoang, L. T., A positive feedback loop between Ethereum and Decentralized Finance (DeFi), Finance Research Letters 43 (2021) 102006.
Fang, F., Chen, Y., Zhang, J., Deep Reinforcement Learning in Digital Asset Management: A Systematic Review, Artificial Intelligence Review 56 (3) (2023) 2155–2190.
Huo, Y., Gao, Y., Enhancing DQN for Crypto-Trading with Technical Indicators and Sentiment Analysis, Applied Soft Computing 115 (2022) 108163.
Lucarelli, G., Borrotti, M., A Deep Reinforcement Learning Approach for Automated Cryptocurrency Trading, Applied Soft Computing 100 (2021) 106905.
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N., Stable-Baselines3: Reliable Reinforcement Learning Implementations, Journal of Machine Learning Research 22 (268) (2021) 1–8.
Sourias, K., Kim, J., Robustness of Reinforcement Learning Agents in Volatile Crypto Markets: A Comparative Study on Ethereum, Expert Systems with Applications 235 (2024) 121114.
Wu, X., Chen, H., Wang, J., Adaptive Deep Q-Learning for Financial Signal Processing and Trading, IEEE Transactions on Neural Networks and Learning Systems 33 (5) (2022) 2041–2055.
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D., Human-Level Control through Deep Reinforcement Learning, Nature 518 (7540) (2015) 529–533.
Sutton, R. S., Barto, A. G., Reinforcement Learning: An Introduction, 2nd ed., MIT Press, Cambridge, MA, 2018.
Theate, T., Ernst, D., An Application of Deep Reinforcement Learning to Algorithmic Trading, Expert Systems with Applications 173 (2021) 114632.
Sattarov, O., Choi, J., Multi-Level Deep Q-Networks for Bitcoin Trading Strategies, Scientific Reports 14 (2024) 1170.
Schnaubelt, M., Deep Reinforcement Learning for the Optimal Placement of Cryptocurrency Limit Orders, European Journal of Operational Research 296 (3) (2022) 993–1006.
Shavandi, A., Khedmati, M., A Multi-Agent Deep Reinforcement Learning Framework for Algorithmic Trading in Financial Markets, Expert Systems with Applications 208 (2022) 118124.
Huang, C. Y., Financial Trading as a Game: A Deep Reinforcement Learning Approach, arXiv preprint arXiv:1807.02787 (2018).
Amirshahi, B., Lahmiri, S., Hybrid Deep Learning and GARCH-Family Models for Forecasting Volatility of Cryptocurrencies, Machine Learning with Applications 12 (2023) 100465.
Gao, L., Comparison of DQN and Double DQN Reinforcement Learning Algorithms for Stock Market Prediction, in Proceedings of the 2023 International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2023), Atlantis Press (2023) 169–177.
Carta, S., Corriga, A., Ferreira, A., Podda, A. S., Recupero, D. R., A Multi-Layer and Multi-Ensemble Stock Trader using Deep Learning and Deep Reinforcement Learning, Applied Intelligence 51 (2021) 889–905.
Hasselt, H. V., Guez, A., Silver, D., Deep Reinforcement Learning with Double Q-Learning, in Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI 2016), AAAI Press (2016) 2094–2100.
Liu, Y., Liu, Q., Zhao, H., Pan, Z., Liu, C., Adaptive Quantitative Trading: An Imitative Deep Reinforcement Learning Approach, in Proceedings of the AAAI Conference on Artificial Intelligence 34 (2020) 2128–2135.
Jing, L., Kang, Y., Automated Cryptocurrency Trading Approach Using Ensemble Deep Reinforcement Learning: Learn to Understand Candlesticks, Expert Systems with Applications 237 (2024) 121373.
Lim, B., Zohren, S., Time-Series Forecasting with Deep Learning: A Survey, Philosophical Transactions of the Royal Society A 379 (2021) 20200209.
Wang, Y., Andreeva, G., Martin-Barragan, B., Machine Learning Approaches to Forecasting Cryptocurrency Volatility: Considering Internal and External Determinants, International Review of Financial Analysis 90 (2023) 102914.
Chakraborty, S., Capturing Financial Markets to Apply Deep Reinforcement Learning, arXiv preprint arXiv:1907.04373 (2019).
Baur, D. G., Dimpfl, T., The Volatility of Bitcoin and Its Role as a Medium of Exchange and a Store of Value, Empirical Economics 61 (5) (2021) 2367–2388.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Information Technology and Business
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
