Reinforcement Learning for Finance: A Python-Based Introduction

Cover
Copyright
Table of Contents
Preface
	Target Audience
	Overview of the Book
	About the Code in This Book
	Conventions Used in This Book
	Using Code Examples
	O’Reilly Online Learning
	How to Contact Us
	Acknowledgments
Part I. The Basics
	Chapter 1. Learning Through Interaction
		Bayesian Learning
			Tossing a Biased Coin
			Rolling a Biased Die
			Bayesian Updating
		Reinforcement Learning
			Major Breakthroughs
			Major Building Blocks
		Deep Q-Learning
		Conclusions
		References
	Chapter 2. Deep Q-Learning
		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
	Chapter 3. Financial Q-Learning
		Finance Environment
		DQL Agent
		Where the Analogy Fails
			Limited Data
			No Impact
		Conclusions
		References
Part II. Data Augmentation
	Chapter 4. Simulated Data
		Noisy Time Series Data
		Simulated Time Series Data
		Conclusions
		References
		DQLAgent Python Class
	Chapter 5. Generated Data
		Simple Example
		Financial Example
		Kolmogorov-Smirnov Test
		Conclusions
		References
Part III. Financial Applications
	Chapter 6. Algorithmic Trading
		Prediction Game Revisited
		Trading Environment
		Trading Agent
		Conclusions
		References
		Finance Environment
		DQLAgent Class
		Simulation Environment
	Chapter 7. Dynamic Hedging
		Delta Hedging
		Hedging Environment
		Hedging Agent
		Conclusions
		References
		BSM (1973) Formula
	Chapter 8. Dynamic Asset Allocation
		Two-Fund Separation
		Two-Asset Case
		Three-Asset Case
		Equally Weighted Portfolio
		Conclusions
		References
		Three-Asset Code
	Chapter 9. Optimal Execution
		The Model
		Model Implementation
		Execution Environment
		Random Agent
		Execution Agent
		Conclusions
		References
	Chapter 10. Concluding Remarks
		References
Index
About the Author
Colophon