burlap.behavior.singleagent.learnfromdemo.mlirl.support

Interface DifferentiableRF

All Superinterfaces:

ParametricFunction, RewardFunction

All Known Implementing Classes:

DiffVFRF, LinearDiffRFVInit, LinearStateActionDifferentiableRF, LinearStateDifferentiableRF

public interface DifferentiableRF
extends RewardFunction, ParametricFunction

An interface for defining differentiable reward functions.

Author:

James MacGlashan.

Nested Class Summary

Nested classes/interfaces inherited from interface burlap.behavior.functionapproximation.ParametricFunction

ParametricFunction.ParametricStateActionFunction, ParametricFunction.ParametricStateFunction

Method Summary

Modifier and Type	Method and Description
FunctionGradient	gradient(State s, Action a, State sprime)

Methods inherited from interface burlap.mdp.singleagent.model.RewardFunction

reward

Methods inherited from interface burlap.behavior.functionapproximation.ParametricFunction

copy, getParameter, numParameters, resetParameters, setParameter

Method Detail

gradient

FunctionGradient gradient(State s,
                          Action a,
                          State sprime)