Kernel-based actor-critic approach with applications.
Baeksuk ChuKeun-Woo JungJooyoung ParkPublished in: Int. J. Fuzzy Log. Intell. Syst. (2011)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- policy gradient
- approximate dynamic programming
- temporal difference
- neuro fuzzy
- gradient method
- reinforcement learning algorithms
- kernel methods
- policy iteration
- support vector machine
- function approximation
- dynamic programming
- average reward
- neural network
- machine learning
- mathematical model
- cost function
- control strategy
- markov decision processes
- optimal policy
- simulated annealing
- learning algorithm