burlap.behavior.valuefunction

Interface QProvider

All Superinterfaces:

QFunction, ValueFunction

All Known Implementing Classes:

ARTDP, BeliefSparseSampling, BoundedRTDP, DifferentiableDP, DifferentiableSparseSampling, DifferentiableVI, DynamicProgramming, FittedVI, GradientDescentSarsaLam, LSPI, PolicyEvaluation, PolicyIteration, PrioritizedSweeping, QLearning, QMDP, RewardValueProjection, RTDP, SarsaLam, SGNaiveQLAgent, SGQWActionHistory, SparseSampling, UCT, ValueIteration, VIModelLearningPlanner

public interface QProvider
extends QFunction

An interface for MDP solvers that can return/compute Q-values. Provides a method for generating the set of relevant Q-values.

Author:

James MacGlashan

Nested Class Summary

Nested Classes

Modifier and Type	Interface and Description
static class	QProvider.Helper A class of helper static methods that may be commonly used by code that uses a QFunction instance.

Method Summary

Modifier and Type	Method and Description
java.util.List<QValue>	qValues(State s) Returns a List of QValue objects for ever permissible action for the given input state.

Methods inherited from interface burlap.behavior.valuefunction.QFunction

qValue

Methods inherited from interface burlap.behavior.valuefunction.ValueFunction

value

Method Detail

qValues

java.util.List<QValue> qValues(State s)

Returns a List of QValue objects for ever permissible action for the given input state.

Parameters:

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

Returns:

a List of QValue objects for ever permissible action for the given input state.