oa::CategoricalActorCritic

Compact default MLP used by discrete-control PPO. It is a convenience model, not a restriction: callers can supply any ActorCritic implementation.

Inheritance

public ActorCritic · public Module

Public Methods

const CategoricalActorCriticConfig & oa::CategoricalActorCritic::config()
ActorCriticOutput oa::CategoricalActorCritic::evaluate(const oa::Matrix & inObservation)

Static Public Methods

static oa::Result<oa::UniquePtr<CategoricalActorCritic>> oa::CategoricalActorCritic::create(const CategoricalActorCriticConfig & inConfig)

Public Method Documentation

const CategoricalActorCriticConfig & oa::CategoricalActorCritic::config()
No public source comment is attached to this declaration.

Returns

const CategoricalActorCriticConfig &

The declared return value.

ActorCriticOutput oa::CategoricalActorCritic::evaluate( const oa::Matrix & inObservation )
No public source comment is attached to this declaration.

Parameters

inObservation
const oa::Matrix &

Returns

ActorCriticOutput

The declared return value.

static oa::Result<oa::UniquePtr<CategoricalActorCritic>> oa::CategoricalActorCritic::create( const CategoricalActorCriticConfig & inConfig )
No public source comment is attached to this declaration.

Parameters

inConfig
const CategoricalActorCriticConfig &

Returns

oa::Result<oa::UniquePtr<CategoricalActorCritic>>

The declared return value.