Computationally intensive and noisy tasks: co-evolutionary learning and temporal difference learning on Backgammon.
Paul J. DarwenPublished in: CEC (2000)
Keyphrases
- temporal difference learning
- computationally intensive
- fixed point
- reinforcement learning
- function approximation
- evaluation function
- approximate value iteration
- learning algorithm
- game playing
- temporal difference
- prior knowledge
- learning process
- active learning
- learning tasks
- monte carlo
- artificial neural networks
- learning environment
- policy iteration
- neural network