burlap.behavior.singleagent.learnfromdemo.mlirl.support

Interface DifferentiableQFunction

All Superinterfaces:

QFunction, ValueFunction

All Known Implementing Classes:

DifferentiableDP, DifferentiableSparseSampling, DifferentiableVI

public interface DifferentiableQFunction
extends QFunction

An interface for a valueFunction that can produce Q-value gradients.

Author:

James MacGlashan.

Method Summary

Modifier and Type	Method and Description
FunctionGradient	qGradient(State s, Action a) Returns the Q-value gradient (QGradientTuple) for the given state and action.

Methods inherited from interface burlap.behavior.valuefunction.QFunction

qValue

Methods inherited from interface burlap.behavior.valuefunction.ValueFunction

value

Method Detail

qGradient

FunctionGradient qGradient(State s,
                           Action a)

Returns the Q-value gradient (QGradientTuple) for the given state and action.

Parameters:

s - the state for which the Q-value gradient is to be returned

a - the action for which the Q-value gradient is to be returned.

Returns:

the Q-value gradient for the given state and action.