Phe-Q: A Pheromone Based Q-Learning.
Ndedi D. MonekossoPaolo RemagninoPublished in: Australian Joint Conference on Artificial Intelligence (2001)
Keyphrases
- reinforcement learning
- ant colony optimization
- cooperative
- function approximation
- learning rate
- multi agent
- state space
- stochastic approximation
- update rule
- learning algorithm
- reinforcement learning algorithms
- model free
- action selection
- artificial ants
- multi agent reinforcement learning
- temporal difference learning
- potential field
- optimal policy
- bucket brigade
- machine learning