Update README.md
This commit is contained in:
11
README.md
11
README.md
@@ -255,16 +255,9 @@
|
|||||||
|
|
||||||
**示例方法**:
|
**示例方法**:
|
||||||
|
|
||||||
- Imitation Learning + Reinforcement Learning
|
- Imitation Learning + Reinforcement Learning:
|
||||||
|
|
||||||
:
|
|
||||||
|
|
||||||
- 先使用监督学习模仿玩家风格,再用强化学习微调策略。
|
- 先使用监督学习模仿玩家风格,再用强化学习微调策略。
|
||||||
|
- AlphaZero-like Framework:
|
||||||
- AlphaZero-like Framework
|
|
||||||
|
|
||||||
:
|
|
||||||
|
|
||||||
- 结合深度强化学习和搜索(如 MCTS),强化对局策略。
|
- 结合深度强化学习和搜索(如 MCTS),强化对局策略。
|
||||||
|
|
||||||
**适用场景**:
|
**适用场景**:
|
||||||
|
|||||||
Reference in New Issue
Block a user