Sigma point policy iteration.
Michael H. BowlingAlborz GeramifardDavid WingatePublished in: AAMAS (1) (2008)
Keyphrases
- policy iteration
- markov decision processes
- fixed point
- least squares
- model free
- sample path
- reinforcement learning
- optimal policy
- finite state
- policy evaluation
- dynamic programming
- average reward
- markov decision process
- temporal difference
- infinite horizon
- linear programming
- markov decision problems
- discounted reward