burlap.behavior.singleagent.learnbydemo.mlirl.support

Interface QGradientPlanner

All Superinterfaces:

QComputablePlanner

All Known Implementing Classes:

DifferentiableSparseSampling, DifferentiableVFPlanner, DifferentiableVI

public interface QGradientPlanner
extends QComputablePlanner

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

Author:

James MacGlashan.

Nested Class Summary

Nested classes/interfaces inherited from interface burlap.behavior.singleagent.planning.QComputablePlanner

QComputablePlanner.QComputablePlannerHelper

Method Summary

Methods

Modifier and Type	Method and Description
java.util.List<QGradientTuple>	getAllQGradients(State s) Returns the list of Q-value gradients (returned as objects) for each action permissible in the given state.
QGradientTuple	getQGradient(State s, GroundedAction a) Returns the Q-value gradient (QGradientTuple) for the given state and action.
void	setBoltzmannBetaParameter(double beta) Sets this planner's Boltzmann beta parameter used to compute gradients.

Methods inherited from interface burlap.behavior.singleagent.planning.QComputablePlanner

getQ, getQs

Method Detail

getAllQGradients

java.util.List<QGradientTuple> getAllQGradients(State s)

Returns the list of Q-value gradients (returned as objects) for each action permissible in the given state.

Parameters:

s - the state for which Q-value gradients are to be returned.

Returns:

the list of Q-value gradients for each action permissible in the given state.

getQGradient

QGradientTuple getQGradient(State s,
                          GroundedAction 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.

setBoltzmannBetaParameter

void setBoltzmannBetaParameter(double beta)

Sets this planner's Boltzmann beta parameter used to compute gradients. As beta gets larger, the policy becomes more deterministic.

Parameters:

beta - the value to which this planner's Boltzmann beta parameter will be set