Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024
This work addresses computational efficiency and robustness for financial trading applications, but it is incremental as it builds on existing ensemble methods with GPU acceleration.
The paper tackled policy instability and sampling bottlenecks in reinforcement learning for financial tasks by revisiting ensemble methods with massively parallel GPU simulations, achieving up to 1,746x faster sampling and improving robustness with up to 4.17% reduced maximum drawdown and 0.21 higher Sharpe ratio.
Reinforcement learning has demonstrated great potential for performing financial tasks. However, it faces two major challenges: policy instability and sampling bottlenecks. In this paper, we revisit ensemble methods with massively parallel simulations on graphics processing units (GPUs), significantly enhancing the computational efficiency and robustness of trained models in volatile financial markets. Our approach leverages the parallel processing capability of GPUs to significantly improve the sampling speed for training ensemble models. The ensemble models combine the strengths of component agents to improve the robustness of financial decision-making strategies. We conduct experiments in both stock and cryptocurrency trading tasks to evaluate the effectiveness of our approach. Massively parallel simulation on a single GPU improves the sampling speed by up to $1,746\times$ using $2,048$ parallel environments compared to a single environment. The ensemble models have high cumulative returns and outperform some individual agents, reducing maximum drawdown by up to $4.17\%$ and improving the Sharpe ratio by up to $0.21$. This paper describes trading tasks at ACM ICAIF FinRL Contests in 2023 and 2024.