策略

class langchain_experimental.rl_chain.base.Policy(**kwargs: Any)

表示策略的抽象类。

方法

__init__(**kwargs)
learn(event)
log(event)
predict(event)
save()

Parameters:

kwargs (任意)

__init__(**kwargs: Any)

Parameters:

kwargs (任意)

abstract learn(event: TEvent) → None

Parameters:

事件 (TEvent)

Return type:

无

abstract log(event: TEvent) → None

Parameters:

事件 (TEvent)

Return type:

无

abstract predict(event: TEvent) → Any

Parameters:

事件 (TEvent)

Return type:

任何

save() → None

Return type:

无