arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.25527cs.LGcs.CE
收藏

DeepSeekMath 遇见订单簿:面向高频方向性交易的组感知策略优化

DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading

Department of Computer Science(计算机科学系);Northwestern University(西北大学);School of Electrical and Computer Engineering(电气与计算机工程学院);Purdue University(普渡大学)

Sayak Charabarty, Souradip Pal

AI总结:

本文通过将基于订单流的状态模型与策略梯度方法结合,研究限价订单簿上的高频交易强化学习,提出组感知策略优化方法,在回测中优于基于价值的 Q-learning 基线。

摘要:

本文通过将基于订单流的状态模型与策略梯度方法配对,研究限价订单簿上的高频交易强化学习。与基于价值的 RL 技术(如表格 Q-learning)不同,我们的方法部署基于策略的方法,如普通 PPO 以及受 DeepSeekMath 启发的变体 GRPO 和 GSPO,这些方法使用组归一化更新和下行感知整形。在使用基于点差缩放奖励的简化回测设置下,对金融资产 AMZN、AAPL 和 GOOG 进行回测,这些新策略在净平均 PnL、盈利能力和回撤方面优于 Q-learning 基线。我们的结果表明:(1) 订单流信号是策略 RL 的合适状态;(2) 组感知 PPO 替代方法优于基于价值的基线。

英文摘要:

This paper studies reinforcement learning for high-frequency trading on limit order books by pairing an Order-Flow-based state model with policy-gradient methods. Instead of value-based RL techniques like tabular Q-learning, our approach deploys policy-based methods like vanilla PPO and DeepSeekMath-inspired variants like GRPO and GSPO, that use group-normalized updates and downside-aware shaping. On backtests with financial assets AMZN, AAPL, and GOOG under a simplified backtesting setup based on spread-scaled rewards, these new policies improve net average PnL, profitability, and drawdown over the Q-Learning baseline. Our results show that (1) Order-Flow signals are an adequate state for policy RL and (2) group-aware PPO surrogates are preferable over value-based baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑