Neural-Fitted TD-Leaf Learning for Playing Othello With Structured Neural Networks.
Sjoerd van den DriesMarco A. WieringPublished in: IEEE Trans. Neural Networks Learn. Syst. (2012)
Keyphrases
- temporal difference learning
- neural network
- board game
- learning algorithm
- game playing
- evaluation function
- learning process
- td learning
- temporal difference
- reinforcement learning
- network architecture
- machine learning
- minimax search
- learning rules
- function approximation
- learning tasks
- supervised learning
- associative memory
- game tree
- monte carlo
- search space