burlap.behavior.singleagent.learnfromdemo.mlirl.support

Interface QGradientPlannerFactory

All Known Implementing Classes:

QGradientPlannerFactory.DifferentiableVIFactory

public interface QGradientPlannerFactory

A factory for generating DifferentiableQFunction objects. This class is use for MultipleIntentionsMLIRL, so that it can generate a different differentiable valueFunction for each cluster; that way, after a maximization step, it can query the policy for each cluster in any state without replanning,rather than using a single valueFunction instance that would require replanning for each cluster (since it would have to switch the reward function).

Author:

James MacGlashan.

Nested Class Summary

Nested Classes

Modifier and Type	Interface and Description
static class	QGradientPlannerFactory.DifferentiableVIFactory A DifferentiableVI factory.

Method Summary

Modifier and Type	Method and Description
DifferentiableQFunction	generateDifferentiablePlannerForRequest(MLIRLRequest request) Returns a DifferentiableQFunction for an MLIRLRequest object's domain, reward function, discount factor, and Boltzmann beta parameter.

Method Detail

generateDifferentiablePlannerForRequest

DifferentiableQFunction generateDifferentiablePlannerForRequest(MLIRLRequest request)

Returns a DifferentiableQFunction for an MLIRLRequest object's domain, reward function, discount factor, and Boltzmann beta parameter.

Parameters:

request - the request defining the problem the valueFunction should solve.

Returns:

a DifferentiableQFunction instance.