A policy iteration algorithm for the American put option and free boundary control problems.
Evangelos F. MagirouParaskevas VassalosNikolaos BarakitisPublished in: J. Comput. Appl. Math. (2020)
Keyphrases
- control problems
- reinforcement learning
- policy iteration algorithm
- optimal control
- markov decision processes
- adaptive control
- actor critic
- infinite horizon
- policy iteration
- state space
- machine learning
- model free
- function approximation
- reinforcement learning algorithms
- dynamic programming
- reinforcement learning methods
- learning algorithm
- approximate dynamic programming
- multi agent