Fuzzy Least Square Policy Iteration and Its Mathematical Analysis.
Farzaneh GhorbaniVali DerhamiMohsen AfsharchiPublished in: Int. J. Fuzzy Syst. (2017)
Keyphrases
- mathematical analysis
- policy iteration
- least squares
- policy evaluation
- sample path
- markov decision processes
- average reward
- reinforcement learning
- fixed point
- optical flow
- markov decision problems
- optimal policy
- optimal control
- markov decision process
- temporal difference
- model free
- finite state
- dynamic programming
- neural network
- image segmentation
- machine learning