PAPER / ARXIV:2610.13126
Jianning Wang, Robert Ślepaczuk, Paweł Sakowski
RESUMO
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), which then initializes reinforcement-learning actors fine-tuned with a risk-aware trading reward. Out-of-sample evaluation over 2024-2026 shows the supervised MLP substantially outperforms passive holding and fixed-time or P&L-based exit rules. Across seven seeds, MLP-initialized Actor-Critic averages 37.54% cumulative return and a Sharpe ratio of 1.705, versus 35.01%/1.651 for the supervised MLP alone and only 0.18% for Actor-Critic trained from scratch.
NO MESMO MAPA
Resumo indisponível. Consulte o paper original.
Resumo indisponível. Consulte o paper original.