Using fuzzy logic for performance evaluation in reinforcement learning.
Hamid R. BerenjiPratap S. KhedkarPublished in: Int. J. Approx. Reason. (1998)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- dynamic programming
- state space
- learning algorithm
- continuous state
- control problems
- supervised learning
- optimal policy
- markov decision processes
- model free
- robotic control
- temporal difference
- action selection
- learning process
- multi agent
- artificial intelligence
- optimal control
- learning problems
- multiscale
- action space
- e learning