# 脸书 AI推出‘ReBeL’：一种算法，将自我强化学习和不完全信息游戏的搜索范式推广

0
3144

1. Foremost, the computation required for 反叛 grows heavy in certain games(such as Recon Chess) with strategic depth but minimal common knowledge.
2. 反叛 relies on knowing the exact rules of the game.
3. 反叛 ’s theoretical guarantees are restricted to two-player zero-sum games, which are comparatively unusual in real-world interactions.