burlap.behavior.singleagent.vfa

Interface DifferentiableStateActionValue

All Superinterfaces:

ParametricFunction, ParametricFunction.ParametricStateActionFunction

All Known Implementing Classes:

LinearFVVFA, LinearVFA

public interface DifferentiableStateActionValue
extends ParametricFunction.ParametricStateActionFunction

An extension of ParametricFunction.ParametricStateActionFunction that is differentiable. Useful for state-action value function approximation (e.g., Q-value function approximation).

Author:

James MacGlashan.

Nested Class Summary

Nested classes/interfaces inherited from interface burlap.behavior.singleagent.vfa.ParametricFunction

ParametricFunction.ParametricStateActionFunction, ParametricFunction.ParametricStateFunction

Method Summary

Methods

Modifier and Type	Method and Description
FunctionGradient	gradient(State s, AbstractGroundedAction a) Returns the gradient of this function.

Methods inherited from interface burlap.behavior.singleagent.vfa.ParametricFunction.ParametricStateActionFunction

evaluate

Methods inherited from interface burlap.behavior.singleagent.vfa.ParametricFunction

copy, getParameter, numParameters, resetParameters, setParameter

Method Detail

gradient

FunctionGradient gradient(State s,
                        AbstractGroundedAction a)

Returns the gradient of this function.

Parameters:

s - the input State

a - the input AbstractGroundedAction

Returns:

the FunctionGradient of this function at the input