Enhancing Nash Q-learning and Team Q-learning mechanisms by using bottlenecks.
Behzad GhazanfariNasser MozayaniPublished in: J. Intell. Fuzzy Syst. (2014)
Keyphrases
- learning mechanisms
- learning algorithm
- learning strategies
- learning mechanism
- reinforcement learning
- domain knowledge
- cognitive architecture
- multi agent
- learning systems
- learning rules
- learning processes
- learning process
- state space
- learning rate
- machine learning
- nash equilibrium
- learning tasks
- active learning
- training data
- individual classifiers
- decision making