PickBestRandomPolicy#

class langchain_experimental.rl_chain.pick_best_chain.PickBestRandomPolicy(feature_embedder: Embedder, **kwargs: Any)[source]#

Random policy for PickBest chain.

Methods

__init__(feature_embedder, **kwargs)

learn(event)

log(event)

predict(event)

save()

Parameters:
__init__(feature_embedder: Embedder, **kwargs: Any)[source]#
Parameters:

  • feature_embedder (Embedder)

  • kwargs (Any)

learn(event: PickBestEvent) → None[source]#
Parameters:

event (PickBestEvent)

Return type:

None

log(event: PickBestEvent) → None[source]#
Parameters:

event (PickBestEvent)

Return type:

None

predict(event: PickBestEvent) → List[Tuple[int, float]][source]#
Parameters:

event (PickBestEvent)

Return type:

List[Tuple[int, float]]

save() → None#
Return type:

None