langchain_experimental.rl_chain.base.VwPolicy

class langchain_experimental.rl_chain.base.VwPolicy(model_repo: ModelRepository, vw_cmd: List[str], feature_embedder: Embedder, vw_logger: VwLogger, *args: Any, **kwargs: Any)

沃普尔瓦比特策略。

方法

__init__(model_repo, vw_cmd, ...)
learn(event)
log(event)
predict(event)
保存()

参数

• model_repo (ModelRepository) –

• vw_cmd (List[str]) –

• feature_embedder (Embedder) –

• vw_logger (VwLogger) –

• args (Any) –

• kwargs (Any) –

__init__(model_repo: ModelRepository, vw_cmd: List[str], feature_embedder: Embedder, vw_logger: VwLogger, *args: Any, **kwargs: Any)

参数

• model_repo (ModelRepository) –

• vw_cmd (List[str]) –

• feature_embedder (Embedder) –

• vw_logger (VwLogger) –

• args (Any) –

• kwargs (Any) –

learn(event: TEvent) → None

参数

事件 (TEvent) –

返回类型

None

log(event: TEvent) → None

参数

事件 (TEvent) –

返回类型

None

predict(event: TEvent) → Any

参数

事件 (TEvent) –

返回类型

Any

save() → None

返回类型

None