Newest papers

MLP-Initialized Reinforcement Learning for Exit Timing in SPX Short-Straddle Portfolios

Jianning Wang, Robert Ślepaczuk, Paweł Sakowski · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.13126 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

本论文研究了SPX短线组合的退出时间,使用两个阶段的监督和增强学习框架。历史性事件首先产生了后期最佳持有/退出标签,以训练多层感知器(MLP)仅使用同时可用的状态变量在部署时。受过培训的MLP随后启动了增强学习的演员,这些演员与风险意识的交易回报进行了精心调整。在2024年至2026年间的非样本评估表明,受监督的MLP显著超过被动持有和代表性的固定时间和利润和损失的退出规则。在七个独立种子中,MLP启动的演员批评平均值为37,54%的累积回报,而Sharpe比例为1.705,与受监督的MLP的35.01%和1.651相比

Machine translation (Meta M2M100); the English original follows.

Abstract

This paper studies exit timing for SPX short-straddle portfolios using a two-stage supervised and reinforcement-learning framework. Historical episodes first generate ex-post optimal hold/exit labels for training a multilayer perceptron (MLP) using only contemporaneously available state variables at deployment. The trained MLP then initializes reinforcement-learning actors that are fine-tuned with a risk-aware trading reward. Out-of-sample evaluation over 2024-2026 shows that the supervised MLP substantially outperforms passive holding and representative fixed-time and profit-and-loss-based exit rules. Across seven independent seeds, MLP-initialized Actor-Critic averages 37.54% cumulative return and a Sharpe ratio of 1.705, compared with 35.01% and 1.651 for the supervised MLP. Actor-Critic trained from scratch averages only 0.18% return. These findings show that oracle-guided supervised learning provides a stable foundation for reward-based policy fine-tuning in a sparse and path-dependent option-exit problem.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Sharpe ratio, Artificial intelligence, Computer science, Machine learning, Reinforcement learning, Supervised learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange