Package net.sf.tweety.arg.prob.reasoner

Class ProbabilisticRankingReasoner

java.lang.Object

net.sf.tweety.arg.prob.reasoner.ProbabilisticRankingReasoner

All Implemented Interfaces:

ModelProvider<Argument,DungTheory,NumericalArgumentRanking>

public class ProbabilisticRankingReasoner
extends java.lang.Object
implements ModelProvider<Argument,DungTheory,NumericalArgumentRanking>

Implements a graded semantics reasoner based on the ideas from [Thimm, Cerutti, Rienstra; 2018].

Author:

Matthias Thimm

Field Summary

Fields

Modifier and Type	Field	Description
private boolean	exactInference	Whether to use exact inference.
static int	NUMBER_OF_TRIALS	Number of trials for the used monte carlo search (this is a factor multiplied with the number of arguments of the actual framework)
private Probability	p	The probability used for all arguments to instantiate a probabilistic argumentation framework
private Semantics	sem	The classical semantics used for evaluating subgraphs

Constructor Summary

Constructors

Constructor	Description
ProbabilisticRankingReasoner(Semantics sem, Probability p, boolean exactInference)	Creates a new reasoner.

Method Summary

Modifier and Type	Method	Description
NumericalArgumentRanking	getModel(DungTheory aaf)	Returns a single (dedicated) model of the given belief base.
java.util.Collection<NumericalArgumentRanking>	getModels(DungTheory bbase)	Returns a characterizing model of the given belief base

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

NUMBER_OF_TRIALS

public static int NUMBER_OF_TRIALS

Number of trials for the used monte carlo search (this is a factor multiplied with the number of arguments of the actual framework)

p

private Probability p

The probability used for all arguments to instantiate a probabilistic argumentation framework

sem

private Semantics sem

The classical semantics used for evaluating subgraphs

exactInference

private boolean exactInference

Whether to use exact inference.

Constructor Detail

ProbabilisticRankingReasoner

public ProbabilisticRankingReasoner(Semantics sem,
                                    Probability p,
                                    boolean exactInference)

Creates a new reasoner.

Parameters:

sem - The classical semantics used for evaluating subgraphs

p - The probability used for all arguments to instantiate a probabilistic argumentation framework

exactInference - Whether to use exact inference.

Method Detail

getModels

public java.util.Collection<NumericalArgumentRanking> getModels(DungTheory bbase)

Description copied from interface: ModelProvider

Returns a characterizing model of the given belief base

Specified by:

getModels in interface ModelProvider<Argument,DungTheory,NumericalArgumentRanking>

Parameters:

bbase - some belief base

Returns:

the (selected) models of the belief base

getModel

public NumericalArgumentRanking getModel(DungTheory aaf)

Description copied from interface: ModelProvider

Returns a single (dedicated) model of the given belief base. If the implemented method allows for more than one dedicated model, the selection may be non-deterministic.

Specified by:

getModel in interface ModelProvider<Argument,DungTheory,NumericalArgumentRanking>

Parameters:

aaf - some belief base

Returns:

a selected model of the belief base.