Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies

TL;DR

This paper explores ensemble reinforcement learning models combined with classifiers to improve financial trading strategies, demonstrating enhanced risk-adjusted returns and stability over individual models.

Contribution

It introduces a novel ensemble approach integrating RL algorithms with classifiers, highlighting the importance of dynamic variance threshold adjustment for optimal performance.

Findings

Ensemble methods outperform individual RL models in risk-adjusted returns.

Dynamic adjustment of variance threshold { au} improves ensemble performance.

Ensemble models better manage drawdowns and stability in trading strategies.

Abstract

This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging classifier models to enhance performance. By combining RL algorithms such as A2C, PPO, and SAC with traditional classifiers like Support Vector Machines (SVM), Decision Trees, and Logistic Regression, we investigate how different classifier groups can be integrated to improve risk-return trade-offs. The study evaluates the effectiveness of various ensemble methods, comparing them with individual RL models across key financial metrics, including Cumulative Returns, Sharpe Ratios (SR), Calmar Ratios, and Maximum Drawdown (MDD). Our results demonstrate that ensemble methods consistently outperform base models in terms of risk-adjusted returns, providing better management of drawdowns and overall stability. However, we identify the sensitivity of ensemble performance to the choice of variance threshold {\tau}, highlighting the importance of dynamic {\tau} adjustment to achieve optimal performance. This study emphasizes the value of combining RL with classifiers for adaptive decision-making, with implications for financial trading, robotics, and other dynamic environments.