burlap.behavior.singleagent.learnfromdemo.mlirl.differentiableplanners.dpoperator

Interface DifferentiableDPOperator

All Superinterfaces:

DPOperator

All Known Implementing Classes:

DifferentiableSoftmaxOperator, SubDifferentiableMaxOperator

public interface DifferentiableDPOperator
extends DPOperator

A DPOperator that is differentiable.

Author:

James MacGlashan.

Method Summary

Modifier and Type	Method and Description
FunctionGradient	gradient(double[] qs, FunctionGradient[] qGradients) Returns the gradient of this DP operator, giving the Q-values on which it operates, their gradient.

Methods inherited from interface burlap.behavior.singleagent.planning.stochastic.dpoperator.DPOperator

apply

Method Detail

gradient

FunctionGradient gradient(double[] qs,
                          FunctionGradient[] qGradients)

Returns the gradient of this DP operator, giving the Q-values on which it operates, their gradient.

Parameters:

qs - the q-values

qGradients - the gradients of the Q-value

Returns:

the gradient of this operator