oa::PolicyEvaluator

Deterministic categorical evaluation over any native OA vector environment. Evaluation is an explicit telemetry boundary: it records the entire horizon first, then performs one execution/synchronization and three compact readbacks.

Static Public Methods

static oa::Result<PolicyEvaluationMetrics> oa::PolicyEvaluator::evaluateCategorical(Environment & inEnvironment, ActorCritic & inModel, const PolicyEvaluationConfig & inConfig = {})

Constructor & Destructor Documentation

oa::PolicyEvaluator::PolicyEvaluator()
No public source comment is attached to this declaration.

Public Method Documentation

static oa::Result<PolicyEvaluationMetrics> oa::PolicyEvaluator::evaluateCategorical( Environment & inEnvironment, ActorCritic & inModel, const PolicyEvaluationConfig & inConfig = {} )
No public source comment is attached to this declaration.

Parameters

inEnvironment
Environment &

inModel
ActorCritic &

inConfig
const PolicyEvaluationConfig &

Default: {}

Returns

oa::Result<PolicyEvaluationMetrics>

The declared return value.