AI 中文总结
研究市场中性投资组合，提出AlphaZeroBeta深度强化学习框架，结合复合奖励函数与CNN-GRU策略，经递归近端策略优化训练及滚动向前协议评估，回测显示该模型在七只股票指数上表现良好，夏普比率高且保持市场中性。
AI 中文摘要
市场中性投资组合旨在抵消系统性市场风险的同时产生持续回报。基于因子模型或凸优化的传统方法在市场格局转变或结构假设失效时往往表现不佳。我们提出了AlphaZeroBeta，这是一个深度强化学习框架，旨在通过接近零的贝塔系数（市场中性）实现相对于基准的阿尔法（超额回报）。AlphaZeroBeta结合了一个复合奖励函数，该函数通过递归近端策略优化（Recurrent PPO）对经过端到端训练的CNN-GRU策略进行风险调整后的超额回报、基准相关性和交易成本的平衡，并通过滚动向前协议进行评估。涵盖2014年至2024年七只股票指数的回测表明，该模型在保持接近零的基准相关性和具有竞争力的回撤的同时，实现了高于基准的夏普比率。
英文摘要
Market-neutral portfolios aim to generate consistent returns while offsetting systematic market risk. Traditional approaches based on factor models or convex optimization often underperform during market regime shifts or when structural assumptions break down. We propose AlphaZeroBeta, a deep reinforcement learning framework designed to deliver benchmark-relative alpha (excess returns) with near-zero beta (market neutrality). AlphaZeroBeta combines a composite reward function that balances risk-adjusted excess return, benchmark correlation, and transaction costs with a CNN-GRU policy trained end-to-end via Recurrent PPO and evaluated through a rolling walk-forward protocol. Backtests covering 2014-2024 across seven equity indices show that the model achieves higher Sharpe ratios than the baselines while maintaining near-zero benchmark correlations and competitive drawdowns.
Comments59 pages, 10 figures. Accepted for publication in Financial Innovation (Springer)
DOI：10.1186/s40854-026-00955-4
