کتاب یادگیری تقویتی برای مالی

یادگیری از طریق تعامل

Bayesian Learning • Tossing a Biased Coin • Rolling a Biased Die • Bayesian Updating • Reinforcement Learning • Major Breakthroughs • Major Building Blocks • Deep Q-Learning • Conclusions • References

یادگیری کیو عمیق

Decision Problems • Dynamic Programming • Q-Learning • CartPole as an Example • The Game Environment • A Random Agent • The DQL Agent • Q-Learning Versus Supervised Learning • Conclusions • References

یادگیری کیو مالی

Finance Environment • DQL Agent • Where the Analogy Fails • Limited Data • No Impact • Conclusions • References

داده‌های شبیه‌سازی شده

Noisy Time Series Data • Simulated Time Series Data • Conclusions • References • DQLAgent Python Class

داده‌های تولید شده

Simple Example • Financial Example • Kolmogorov-Smirnov Test • Conclusions • References

معاملات الگوریتمی

Prediction Game Revisited • Trading Environment • Trading Agent • Conclusions • References • Finance Environment • DQLAgent Class • Simulation Environment

پوشش ریسک پویا

Delta Hedging • Hedging Environment • Hedging Agent • Conclusions • References • BSM (1973) Formula

تخصیص دارایی پویا

Two-Fund Separation • Two-Asset Case • Three-Asset Case • Equally Weighted Portfolio • Conclusions • References • Three-Asset Code

اجرای بهینه

The Model • Model Implementation • Execution Environment • Random Agent • Execution Agent • Conclusions • References

نکات پایانی

References