Learning-Rate Adjusting Q-Learning for Prisoner's Dilemma Games.
Koichi MoriyamaPublished in: IAT (2008)
Keyphrases
- learning rate
- convergence rate
- learning algorithm
- error function
- hidden layer
- adaptive learning rate
- nash equilibrium
- rapid convergence
- weight vector
- nash equilibria
- game theory
- multilayer neural networks
- convergence speed
- computer games
- reinforcement learning
- activation function
- stochastic games
- convergence theorem
- back propagation
- machine learning
- neural network