Othello and chess program is sometimes referred to as the AI (artificial intelligence). Many of them choose the best move using the evaluation function, the look-ahead function, and the computing power of the computer. This way is to say brute force rather than intelligence.
This program (Tictactoe Evo) will determine the move like shake the dice without the evaluation function and the look-ahead function, but would be given a reward if win, fined if lose after the match. Tic-tac-toe Evo would be choose the best move by repeating this procedure.
This is referred to as the evolutional algorithm.
- Machine Learning
- It expressed in the degree of evolution from "H. pylori" to "human beings".
- Better player, evolution will be accelerated.
- Supported one player gameplay.
- Starting first (X), starting second (O) will be determined at random.
I will not give in to such a H. pylori!
for PC: https://happyclam.github.io/tictactoe-evo/
Latest Version
1.4.5Uploaded by
Baxtear Hawlire
Requires Android
Android 4.0+
Category
Free Board GameContent Rating
Everyone
Report
Flag as inappropriateLast updated on Nov 14, 2018
Restored how to give rewards during reinforcement learning.
