Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning
Abstract
This study aims to determine whether the application of Deep Reinforcement Learning (DRL) as a specialized execution overlay can enhance pair trading in highly volatile cryptocurrency markets. Although classical implementations of the strategy have proven successful in traditional equities, they frequently exhibit rigidity and suffer from severe divergence risks when applied to high-variance environments. To construct a robust system, we developed a hierarchical "Filter-then-Rank" pair selection methodology and a custom "Fixed Risk, Adaptive Mean" execution model. The system employs a Proximal Policy Optimization (PPO) agent with a Long Short-Term Memory (LSTM) layer to govern execution decisions within strict deterministic risk management boundaries. Evaluated on 1-hour interval data from the Binance USD-M Futures market, the selected RL policy achieved an Out-Of-Sample performance that substantially outperformed the heuristic baseline, although the results varied considerably across five random seeds, with four of the five seeds exceeding the baseline in both CAGR and Sortino Ratio. A stationary circular block bootstrap test of the Agent's risk-adjusted outperformance yields p-values of approximately 0.06, which fall just short of the conventional 5% significance threshold. Ultimately, this study contributes to the quantitative finance literature by introducing a hybrid architecture that combines statistical arbitrage with DRL execution policies. Furthermore, it applies safe reinforcement learning via deterministic shielding, with results indicating that anchoring a neural policy to statistically robust boundaries mitigates severe divergence risks.
Related
- Context-Guided Traversal with Deep Reinforcement Learning for Suspicious Subgraph Detection in Cryptocurrency Transaction Graphs
- A Power Regulation Strategy for Grid-Forming Wind Power Clusters Based on Deep Reinforcement Learning
- Augmented Patient Preference Incorporated Reinforcement Learning (APP-RL) to Estimate the Optimal Dynamic Treatment Regime
- An Improved Escape Algorithm with Reinforcement Learning and Multi-Strategy Synergy for Global Optimization and Real Problems
- Reinforcement Learning for Global-Local Control of Dynamic Networks with Applications to Systemic Risk
BibTeX
@misc{lebiedz2026dynamic,
title = {{Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning}},
author = {Damian Lebiedź and Robert Ślepaczuk},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.04574},
eprint = {2606.04574},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.04574},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning
AU - Damian Lebiedź
AU - Robert Ślepaczuk
PY - 2026
DA - 2026/10/31
PB - arXiv
DO - 10.48550/arxiv.2606.04574
UR - https://arxiv.org/abs/2606.04574
AB - This study aims to determine whether the application of Deep Reinforcement Learning (DRL) as a specialized execution overlay can enhance pair trading in highly volatile cryptocurrency markets. Although classical implementations of the strategy have proven successful in traditional equities, they frequently exhibit rigidity and suffer from severe divergence risks when applied to high-variance environments. To construct a robust system, we developed a hierarchical "Filter-then-Rank" pair selection methodology and a custom "Fixed Risk, Adaptive Mean" execution model. The system employs a Proximal Policy Optimization (PPO) agent with a Long Short-Term Memory (LSTM) layer to govern execution decisions within strict deterministic risk management boundaries. Evaluated on 1-hour interval data from the Binance USD-M Futures market, the selected RL policy achieved an Out-Of-Sample performance that substantially outperformed the heuristic baseline, although the results varied considerably across five random seeds, with four of the five seeds exceeding the baseline in both CAGR and Sortino Ratio. A stationary circular block bootstrap test of the Agent's risk-adjusted outperformance yields p-values of approximately 0.06, which fall just short of the conventional 5% significance threshold. Ultimately, this study contributes to the quantitative finance literature by introducing a hybrid architecture that combines statistical arbitrage with DRL execution policies. Furthermore, it applies safe reinforcement learning via deterministic shielding, with results indicating that anchoring a neural policy to statistically robust boundaries mitigates severe divergence risks.
ER -