Foundations of Reinforcement Learning with Applications in Finance

Ashwin Rao, Tikhon Jelvis  ·  2023

Reference. Rao, A. & Jelvis, T. (2023). Foundations of Reinforcement Learning with Applications in Finance. Chapman & Hall/CRC. ISBN 978-1-032-12412-4.  [link]

  • Claim: Asset allocation, derivatives pricing and hedging, and order-book trading are sequential decisions under uncertainty, and can be solved as Markov decision processes.
  • Method: MDP formulations of each finance problem, then dynamic programming, approximate DP and RL algorithms, all implemented in Python.
  • Matters: The SPEC 3.2 Systematic Market-Making homework is built directly on this book and its code (e.g. Markov processes in HW2).
  • Connects to: FBAQuant: deep hedging with RL · Cartea–Jaimungal–Penalva for order-book trading (its ch. 10)
  • Code: https://github.com/TikhonJelvis/RL-book
Foundations of Reinforcement Learning with Applications in Finance cover
Cover of Foundations of Reinforcement Learning with Applications in Finance on the Open Library.