Reinforcement learning for training a computer program of Chinese chess.
Wing-Kwong WongHan-Hung ChenSheng-Cheng HsuPublished in: Int. J. Intell. Inf. Database Syst. (2009)
Keyphrases
- reinforcement learning
- computer programs
- computer chess
- computer software
- evaluation function
- training sessions
- medical students
- supervised learning
- training program
- artificial intelligence
- training examples
- model free
- computer hardware
- computer programming
- temporal difference
- brute force
- training process
- computer skills
- learning algorithm
- static analysis
- machine learning
- state space
- markov decision processes
- online learning
- imperfect information
- multi agent
- dynamic programming
- programming language
- text classification
- game tree search
- training algorithm
- computer systems
- optimal policy
- learning problems
- computer technology
- function approximation
- training phase