Saved in:
Bibliographic Details
Main Authors: Amirzadeh, Rasoul, Thiruvady, Dhananjay, Nazari, Asef, Ee, Mong Shan
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.09462
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913472745308160
author Amirzadeh, Rasoul
Thiruvady, Dhananjay
Nazari, Asef
Ee, Mong Shan
author_facet Amirzadeh, Rasoul
Thiruvady, Dhananjay
Nazari, Asef
Ee, Mong Shan
contents Despite advances in artificial intelligence-enhanced trading methods, developing a profitable automated trading system remains challenging in the rapidly evolving cryptocurrency market. This research focuses on developing a reinforcement learning (RL) framework to tackle the complexities of trading five prominent altcoins: Binance Coin, Ethereum, Litecoin, Ripple, and Tether. To this end, we present the CausalReinforceNet~(CRN) framework, which integrates both Bayesian and dynamic Bayesian network techniques to empower the RL agent in trade decision-making. We develop two agents using the framework based on distinct RL algorithms to analyse performance compared to the Buy-and-Hold benchmark strategy and a baseline RL model. The results indicate that our framework surpasses both models in profitability, highlighting CRN's consistent superiority, although the level of effectiveness varies across different cryptocurrencies.
format Preprint
id arxiv_https___arxiv_org_abs_2310_09462
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading
Amirzadeh, Rasoul
Thiruvady, Dhananjay
Nazari, Asef
Ee, Mong Shan
Artificial Intelligence
Machine Learning
Despite advances in artificial intelligence-enhanced trading methods, developing a profitable automated trading system remains challenging in the rapidly evolving cryptocurrency market. This research focuses on developing a reinforcement learning (RL) framework to tackle the complexities of trading five prominent altcoins: Binance Coin, Ethereum, Litecoin, Ripple, and Tether. To this end, we present the CausalReinforceNet~(CRN) framework, which integrates both Bayesian and dynamic Bayesian network techniques to empower the RL agent in trade decision-making. We develop two agents using the framework based on distinct RL algorithms to analyse performance compared to the Buy-and-Hold benchmark strategy and a baseline RL model. The results indicate that our framework surpasses both models in profitability, highlighting CRN's consistent superiority, although the level of effectiveness varies across different cryptocurrencies.
title A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.09462