burlap.behavior.functionapproximation

Interface DifferentiableStateActionValue

All Superinterfaces:

ParametricFunction, ParametricFunction.ParametricStateActionFunction

All Known Implementing Classes:

DenseLinearVFA, DenseStateActionLinearVFA, 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.functionapproximation.ParametricFunction

ParametricFunction.ParametricStateActionFunction, ParametricFunction.ParametricStateFunction

Method Summary

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

Methods inherited from interface burlap.behavior.functionapproximation.ParametricFunction.ParametricStateActionFunction

evaluate

Methods inherited from interface burlap.behavior.functionapproximation.ParametricFunction

copy, getParameter, numParameters, resetParameters, setParameter

Method Detail

gradient

FunctionGradient gradient(State s,
                          Action a)

Returns the gradient of this function.

Parameters:

s - the input State

a - the input Action

Returns:

the FunctionGradient of this function at the input