Foundations of Reinforcement Learning with Applications in Finance

ISBN-13: 9781032124124 / Angielski / Twarda / 2022 / 598 str.

Tikhon Jelvis

Opis

This book demystifies Reinforcement Learning, and makes it a practically useful tool for those studying and working in applied areas, especially finance. This book seeks to overcome that barrier, and to introduce the foundations of RL in a way that balances depth of understanding with clear, minimally technical delivery.

Recenzje

“This book is a nice addition to the literature on Reinforcement Learning (RL), offering comprehensive coverage of both foundational RL techniques and their applications in the field of finance. It has the potential to be a foundational reference for both practitioners and researchers in finance. The book delves into essential RL concepts such as Markov Decision Processes (MDPs), Dynamic Programming, Policy Optimization, Actor-Critic models, Multi-armed Bandits, and Regret Bounds.

Despite its finance-oriented approach, individuals without an extensive financial background but possessing a decent machine learning (ML) background will find it easy to read this book.

By encompassing all of the major asset classes including equities, fixed income and derivatives, the book caters to a broad range of readers, enabling them to apply RL techniques to diverse financial scenarios. In summary, this book is an outstanding resource that combines RL fundamentals with practical applications in finance.”
– Natesh Pillai, Department of Statistics, Harvard University, Unites States of America

Spis treści

Section I. Processes and Planning Algorithms. 1. Markov Processes. 2. Markov Decision Processes. 3. Dynamic Programming Algorithms. 4. Function Approximation and Approximate Dynamic Programming. Section II. Modeling Financial Applications. 5. Utility Theory. 6. Dynamic Asset-Allocation and Consumption. 7. Derivatives Pricing and Hedging. 8. Order-Book Trading Algorithms. Section III. Reinforcement Learning Algorithms. 9. Monte-Carlo and Temporal-Difference for Prediction. 10. Monte-Carlo and Temporal-Difference for Control. 11. Batch RL, Experience-Replay, DQN, LSPI, Gradient TD. 12. Policy Gradient Algorithms. Section IV. Finishing Touches. 13. Multi-Armed Bandits: Exploration versus Exploitation. 14. Blending Learning and Planning. 15. Summary and Real-World Considerations. Appendices.