使用actor-critic计算的赛马娘决策AI。
game里写的是简化版的赛马娘游戏逻辑，只有训练和休息，没有比赛。 训练后能够比50体力以上时只选当回合加最大属性值的训练，50体力以下时休息的贪婪算法每局收益更高，证明《赛马娘》游戏存在跨回合策略。
-
Notifications
You must be signed in to change notification settings - Fork 1
ZZZZkp/UmaMusumeRL
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Tried to use reinforcement learning trainning UmaMusume AI but failed
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published