Policy iteration for american options: overview.
Christian BenderAnastasia KolodkoJohn SchoenmakersPublished in: Monte Carlo Methods Appl. (2006)
Keyphrases
- policy iteration
- markov decision processes
- model free
- least squares
- optimal policy
- fixed point
- reinforcement learning
- sample path
- average reward
- temporal difference
- finite state
- policy evaluation
- linear programming
- infinite horizon
- markov decision problems
- optimal control
- convergence rate
- markov decision process
- neural network
- state space
- function approximation
- dynamic programming
- discounted reward