Temporal Difference Learning for the Game Tic-Tac-Toe 3D: Applying Structure to Neural Networks.
Michiel Van De SteegMadalina M. DruganMarco A. WieringPublished in: SSCI (2015)
Keyphrases
- game playing
- temporal difference learning
- tic tac toe
- neural network
- video games
- computer games
- temporal difference
- artificial neural networks
- monte carlo tree search
- game based learning
- game play
- game design
- function approximation
- attitudes toward
- game development
- fixed point
- dynamic environments
- reinforcement learning