Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation.
Simon M. LucasThomas Philip RunarssonPublished in: CIG (2006)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- evaluation function
- game playing
- reinforcement learning
- temporal difference
- reinforcement learning algorithms
- markov decision process
- neural network
- decision making
- optimal solution
- state space
- supervised learning
- virtual environment
- radial basis function