📝 SummarXiv

Abstract

Deep reinforcement learning has shown promise in trade execution, yet its use in low-frequency factor portfolio construction remains under-explored. A key obstacle is the high-dimensional, unbalanced state space created by stocks that enter and exit the investable universe. We introduce Conditional Auto-encoded Factor-based Portfolio Optimisation (CAFPO), which compresses stock-level returns into a small set of latent factors conditioned on 94 firm-specific characteristics. The factors feed a DRL agent implemented with both PPO and DDPG to generate continuous long-short weights. On 20 years of U.S. equity data (2000--2020), CAFPO outperforms equal-weight, value-weight, Markowitz, vanilla DRL, and Fama--French-driven DRL, delivering a 24.6\% compound return and a Sharpe ratio of 0.94 out of sample. SHAP analysis further reveals economically intuitive factor attributions. Our results demonstrate that factor-aware representation learning can make DRL practical for institutional, low-turnover portfolio management.