mlsanityData to 14 Oct 2026

Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning

arXiv 2606.04574 ↗First posted 3 Jun 2026cs.LG cs.NE q-fin.STcited by 0

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

Abstract (arXiv)

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 address this need, this research introduces novel concepts. To construct a robust system, we developed a hierarchical "Filter-then-Rank" pair selection methodology and a proprietary "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 optimized RL policy achieved an out-of-sample performance that substantially outperformed the heuristic baseline. A stationary circular block bootstrap robustness check confirms that the agent's risk-adjusted outperformance is statistically significant at the 10 percent level. Although falling marginally short of the stricter 5 percent threshold, this result highlights the extreme idiosyncratic variance characteristic of digital assets. Ultimately, this thesis contributes to the quantitative finance literature by introducing a hybrid architecture that combines statistical arbitrage with DRL execution policies. Furthermore, it delivers a novel framework for safe reinforcement learning via deterministic shielding, proving that anchoring a neural policy to statistically robust boundaries successfully mitigates severe divergence risks.

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 8 of its 43 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

8 of 43 references.

References · 8

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPOcited by 186
  3. 2017A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problemcited by 128
  4. 2020FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Financecited by 87
  5. 2017Time Limits in Reinforcement Learningcited by 79
  6. 2021Deep Learning Statistical Arbitragecited by 13
  7. 2025RegimeFolio: A Regime Aware ML System for Sectoral Portfolio Optimization in Dynamic Marketscited by 7
  8. 2024Statistical arbitrage in multi-pair trading strategy based on graph clustering algorithms in US equities marketcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Reinforcement Learning Pair Trading: A Dynamic Scaling approach
  2. 2024Optimizing Portfolio with Two-Sided Transactions and Lending: A Reinforcement Learning Framework
  3. 2025Cryptocurrency Portfolio Management with Reinforcement Learning: Soft Actor--Critic and Deep Deterministic Policy Gradient Algorithms
  4. 2024A Deep Reinforcement Learning Approach for Trading Optimization in the Forex Market with Multi-Agent Asynchronous Distribution
  5. 2022Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets
  6. 2025Can Artificial Intelligence Trade the Stock Market?
  7. 2024Modelling crypto markets by multi-agent reinforcement learning
  8. 2024Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization