Strategy Acquisition for the Game "Othello" Based on Reinforcement Learning.
Taku YoshiokaShin IshiiMinoru ItoPublished in: ICONIP (1998)
Keyphrases
- game playing
- temporal difference learning
- reinforcement learning
- board game
- temporal difference
- game tree
- minimax search
- evaluation function
- game tree search
- function approximation
- optimal strategy
- video games
- reinforcement learning algorithms
- computer games
- monte carlo
- markov decision processes
- fixed point
- opponent modeling
- game play
- imperfect information
- learning algorithm
- world class
- learning process
- dynamic programming
- state space
- educational games
- step size
- game theory
- policy iteration
- search algorithm
- attitudes toward