burlap.mdp.singleagent.model

Class FactoredModel

java.lang.Object

burlap.mdp.singleagent.model.FactoredModel

All Implemented Interfaces:

FullModel, SampleModel, TaskFactoredModel

public class FactoredModel
extends java.lang.Object
implements TaskFactoredModel, FullModel

A FactoredModel is an implementation of a SampleModel or FullModel that computes transitions using a SampleStateModel, RewardFunction and TerminalFunction.

Author:

James MacGlashan.

Nested Class Summary

Nested classes/interfaces inherited from interface burlap.mdp.singleagent.model.FullModel

FullModel.Helper

Field Summary

Fields

Modifier and Type	Field and Description
protected RewardFunction	rf
protected SampleStateModel	stateModel
protected TerminalFunction	tf

Constructor Summary

Constructors

Constructor and Description
FactoredModel()
FactoredModel(SampleStateModel stateModel, RewardFunction rf, TerminalFunction tf) Initializes

Method Summary

Modifier and Type	Method and Description
RewardFunction	getRf()
SampleStateModel	getStateModel()
TerminalFunction	getTf()
RewardFunction	rewardFunction() Returns the RewardFunction this model uses to compute rewards
EnvironmentOutcome	sample(State s, Action a) Samples a transition from the transition distribution and returns it.
void	setRf(RewardFunction rf)
void	setStateModel(SampleStateModel stateModel)
void	setTf(TerminalFunction tf)
boolean	terminal(State s) Indicates whether a state is a terminal state (i.e., no more action occurs and zero reward received from there on out)
TerminalFunction	terminalFunction() Returns the TerminalFunction this model uses to determine terminal states
java.util.List<TransitionProb>	transitions(State s, Action a) Returns the set of possible transitions when Action is applied in State s.
void	useRewardFunction(RewardFunction rf) Tells this model to use the corresponding RewardFunction
void	useTerminalFunction(TerminalFunction tf) Tells this model to use the corresponding TerminalFunction

Methods inherited from class java.lang.Object

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

Field Detail

stateModel

protected SampleStateModel stateModel

rf

protected RewardFunction rf

tf

protected TerminalFunction tf

Constructor Detail

FactoredModel

public FactoredModel()

FactoredModel

public FactoredModel(SampleStateModel stateModel,
                     RewardFunction rf,
                     TerminalFunction tf)

Initializes

Parameters:

stateModel - the SampleStateModel to use

rf - the RewardFunction to use

tf - the TerminalFunction to use

Method Detail

useRewardFunction

public void useRewardFunction(RewardFunction rf)

Description copied from interface: TaskFactoredModel

Tells this model to use the corresponding RewardFunction

Specified by:

useRewardFunction in interface TaskFactoredModel

Parameters:

rf - the RewardFunction

useTerminalFunction

public void useTerminalFunction(TerminalFunction tf)

Description copied from interface: TaskFactoredModel

Tells this model to use the corresponding TerminalFunction

Specified by:

useTerminalFunction in interface TaskFactoredModel

Parameters:

tf - the TerminalFunction

rewardFunction

public RewardFunction rewardFunction()

Description copied from interface: TaskFactoredModel

Returns the RewardFunction this model uses to compute rewards

Specified by:

rewardFunction in interface TaskFactoredModel

Returns:

the RewardFunction this model uses to compute rewards

terminalFunction

public TerminalFunction terminalFunction()

Description copied from interface: TaskFactoredModel

Returns the TerminalFunction this model uses to determine terminal states

Specified by:

terminalFunction in interface TaskFactoredModel

Returns:

the TerminalFunction this model uses to determine terminal states

sample

public EnvironmentOutcome sample(State s,
                                 Action a)

Description copied from interface: SampleModel

Samples a transition from the transition distribution and returns it.

Specified by:

sample in interface SampleModel

Parameters:

s - the source state

a - the action taken in the source state

Returns:

and EnvironmentOutcome describing the sampled transition

transitions

public java.util.List<TransitionProb> transitions(State s,
                                                  Action a)

Description copied from interface: FullModel

Returns the set of possible transitions when Action is applied in State s. The returned list only needs to include transitions that have non-zero probability of occurring.

Specified by:

transitions in interface FullModel

Parameters:

s - the source State

a - the Action applied in the source state

Returns:

the probability distribution over possible transitions.

getStateModel

public SampleStateModel getStateModel()

setStateModel

public void setStateModel(SampleStateModel stateModel)

getRf

public RewardFunction getRf()

setRf

public void setRf(RewardFunction rf)

getTf

public TerminalFunction getTf()

setTf

public void setTf(TerminalFunction tf)

terminal

public boolean terminal(State s)

Description copied from interface: SampleModel

Indicates whether a state is a terminal state (i.e., no more action occurs and zero reward received from there on out)

Specified by:

terminal in interface SampleModel

Parameters:

s - the input state to test

Returns:

true if the state is a terminal state, false if it is not.