具有漂移不确定性的鲁棒探索性均值-方差问题
Robust exploratory mean-variance problem with drift uncertainty
摘要：
本文解决了具有漂移不确定性的鲁棒探索性均值-方差问题中的极小-极大问题。证明了稳健投资者在一个容许集中选择具有最小$L^2$范数的Sharpe比率。均值-方差问题中的强化学习框架提供了一种探索-利用权衡机制;如果我们另外考虑模型的不确定性，则鲁棒策略本质上更多地考虑利用而不是探索，因此反映了更保守的优化方案。最后，我们使用财务数据回测稳健探索性投资的表现，发现稳健策略可以超越纯粹的探索性策略，并抵御熊市中的下行风险。
英文摘要：
We solve a min-max problem in a robust exploratory mean-variance problem with drift uncertainty in this paper. It is verified that robust investors choose the Sharpe ratio with minimal $L^2$ norm in an admissible set. A reinforcement learning framework in the mean-variance problem provides an exploration-exploitation trade-off mechanism; if we additionally consider model uncertainty, the robust strategy essentially weights more on exploitation rather than exploration and thus reflects a more conservative optimization scheme. Finally, we use financial data to backtest the performance of the robust exploratory investment and find that the robust strategy can outperform the purely exploratory strategy and resist the downside risk in a bear market.
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。
