Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024
On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance
Abstract (arXiv)
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× 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.
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 17 of its 32 references that are in the map. First posted on arXiv 18 Jan 2025.
Builds on
17 of 32 references.
References · 17
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
- 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
- 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
- 2017Deep Reinforcement Learning that Matterscited by 754
- 2019Monte Carlo Gradient Estimation in Machine Learningcited by 283
- 2021Recent Advances in Reinforcement Learning in Financecited by 110
- 2019Deep Reinforcement Learning for Tradingcited by 73
- 2021FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Financecited by 58
- 2019Measuring the Reliability of Reinforcement Learning Algorithmscited by 51
5 more
- 2018Practical Deep Reinforcement Learning Approach for Stock Tradingcited by 49
- 2021ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Marketscited by 36
- 2023Dynamic Datasets and Market Environments for Financial Reinforcement Learningcited by 15
- 2023JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for tradingcited by 14
- 2020Option Hedging with Risk Averse Reinforcement Learningcited by 13
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy
- 2025Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies
- 2025FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading
- 2024A Deep Reinforcement Learning Framework For Financial Portfolio Management
- 2024Learning the Market: Sentiment-Based Ensemble Trading Agents
- 2025Cryptocurrency Portfolio Management with Reinforcement Learning: Soft Actor--Critic and Deep Deterministic Policy Gradient Algorithms
- 2025The Red Queen's Trap: Limits of Deep Evolution in High-Frequency Trading
- 2026Can AI Make Money in Crypto? Measuring the Gap from Backtests to Real Markets