Module policy 

Module for implementing a policy.

Structs

ActionContext

An action along with additional context about the decision.

AsyncPolicy

An asynchronous policy using an inference server with autobatching.

RLTrainOutput

A training output.

Traits

Batchable

Trait for a type that can be batched and unbatched (split).

Policy

Trait for a RL policy.

PolicyLearner

Learner for a policy.

PolicyState

The state of a policy.

ToAction

Defines how an environment’s action is converted to a policy’s action.

ToObservation

Defines how an environment’s state is converted to a policy’s observation.

Type Aliases

LearnerTransitionBatch

Batched transitions for a PolicyLearner.