跳至正文
返回文库全部文档

强化学习动态调整加密货币配对交易规模

文章 arXiv papers · 作者: Hongshen Yang et al.
阅读原文

总结

本研究考察强化学习能否改进加密货币配对交易。配对交易是一种统计套利方法，通过交易相关资产之间的价格差获利。作者构建交易环境并训练智能体选择加密货币配对交易的时机和方式。他们还为学习任务设计奖励塑形以及观测和行动空间，旨在动态调整交易决策。

实验使用逐分钟的 BTC-GBP 和 BTC-EUR 数据。报告的传统配对交易年化利润为 8.33%，而受测强化学习智能体的年化利润介于 9.94% 至 31.53%，具体取决于学习算法。这些结果表明，所报告实验中的历史表现更强，但本身并不能证明实盘盈利能力。本文未说明交易成本、风险调整后比较或样本外验证细节，因此应结合所述数据和评估范围理解这些结果。

核心观点

  • 研究将强化学习应用于相关加密货币之间的配对交易。
  • 智能体在构建的环境中学习选择交易时机和规模。
  • 该方法采用定制的奖励塑形以及观测和行动空间。
  • 实验涵盖 BTC-GBP 和 BTC-EUR 的逐分钟数据。
  • 报告的 RL 利润区间高于传统策略结果，但摘要未说明实盘稳健性和成本。

标签

加密资产配对交易套利机器学习回测
全文
# Reinforcement Learning Pair Trading: A Dynamic Scaling approach


# Reinforcement Learning Pair Trading: A Dynamic Scaling approach









Cryptocurrency is a cryptography-based digital asset with extremely volatile prices. Around USD 70 billion worth of cryptocurrency is traded daily on exchanges. Trading cryptocurrency is difficult due to the inherent volatility of the crypto market. This study investigates whether Reinforcement Learning (RL) can enhance decision-making in cryptocurrency algorithmic trading compared to traditional methods. In order to address this question, we combined reinforcement learning with a statistical arbitrage trading technique, pair trading, which exploits the price difference between statistically correlated assets. We constructed RL environments and trained RL agents to determine when and how to trade pairs of cryptocurrencies. We developed new reward shaping and observation/action spaces for reinforcement learning. We performed experiments with the developed reinforcement learner on pairs of BTC-GBP and BTC-EUR data separated by 1 min intervals (n=263,520). The traditional non-RL pair trading technique achieved an annualized profit of 8.33%, while the proposed RL-based pair trading technique achieved annualized profits from 9.94% to 31.53%, depending upon the RL learner. Our results show that RL can significantly outperform manual and traditional pair trading techniques when applied to volatile markets such as~cryptocurrencies.

在遵守原作品许可的前提下，附作者信息全文展示。 许可协议: abstract CC0

此摘要由 Stratmill 研究智能体根据原文撰写，并非原文副本。