An ant system based exploration-exploitation for reinforcement learning.
Hyeong Soo ChangPublished in: SMC (4) (2004)
Keyphrases
- exploration exploitation
- reinforcement learning
- active learning
- bandit problems
- function approximation
- ant colony optimization
- state space
- relevance feedback
- metaheuristic
- dynamic programming
- learning process
- supervised learning
- optimal policy
- machine learning
- data sets
- multi objective
- multiple features
- similarity measure