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

arXiv 2502.17518 ↗First posted 23 Feb 2025cs.LG cs.AI q-fin.CPcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

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 original experimental results demonstrate that ensemble methods often outperform base models in terms of risk-adjusted returns, providing better management of drawdowns and overall stability. However, both the original analysis and the additional reproduction reported in this version show that ensemble performance is sensitive to the choice of variance threshold (τ), classifier group, RL-agent pair, and market universe. The reproduction evidence strengthens the conclusion that classifier-assisted ensemble selection can improve robustness, while also clarifying that the advantage is conditional rather than automatic across all datasets. This study emphasizes the value of combining RL with classifiers for adaptive decision-making, with implications for financial trading, robotics, and other dynamic environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 33 references that are in the map. First posted on arXiv 23 Feb 2025.

Builds on

18 of 33 references.

References · 18

2017Constrained Policy Optimizationcited by 983
2016Deep Exploration via Bootstrapped DQNcited by 527
2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 337
2021Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemblecited by 302
2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
2019Safe Reinforcement Learning Using Robust MPCcited by 85
2021Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPscited by 80
2022Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matterscited by 76
2019Worst Cases Policy Gradientscited by 52
2020Neurosymbolic Reinforcement Learning with Formally Verified Explorationcited by 49
2019Accurate Uncertainty Estimation and Decomposition in Ensemble Learningcited by 42
2021Model-based Constrained Reinforcement Learning using Generalized Control Barrier Functioncited by 32

6 more

2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 31
2024Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learningcited by 31
2021Density Constrained Reinforcement Learningcited by 25
2022One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learningcited by 23
2021Risk-sensitive safety analysis using Conditional Value-at-Riskcited by 14
2024Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimizationcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way