About this document
Theory by sans.suryadevara is a document available to read on EtoBox.
This paper presents a reinforcement learning approach to optimal stopping problems, particularly for pricing option-type products like swing options. The authors utilize deep Q-learning to model the action-value function, allowing for efficient computation of optimal exercise strategies without the need for predefined basis functions. The methodology is demonstrated through examples and includes the derivation of bounds on option prices, showcasing its applicability in mathematical finance.
- Author
- sans.suryadevara
- Language
- EN