burlap.behavior.singleagent.learning.modellearning.artdp

Class ARTDP

java.lang.Object

burlap.behavior.singleagent.MDPSolver

burlap.behavior.singleagent.learning.modellearning.artdp.ARTDP

All Implemented Interfaces:

LearningAgent, MDPSolverInterface, QFunction, ValueFunction

public class ARTDP
extends MDPSolver
implements QFunction, LearningAgent

This class provides an implementation of Adaptive Realtime Dynamic Programming [1]. By default, a tabular model will be used and a boltzmann distribution with a temperature of 0.1 will be used. A different model can be provided in the constructor as well as the value function initialization used. The policy followed may be set with a setter (setPolicy(burlap.behavior.policy.SolverDerivedPolicy)). The Q-value assigned to state-action pairs for entirely untried transitions is reported as that returned by the value function initializer provided. In general, value function initialization should always be optimistic. 1. Barto, Andrew G., Steven J. Bradtke, and Satinder P. Singh. "Learning to act using real-time dynamic programming." Artificial Intelligence 72.1 (1995): 81-138.

Author:

James MacGlashan

Nested Class Summary

Nested classes/interfaces inherited from interface burlap.behavior.valuefunction.QFunction

QFunction.QFunctionHelper

Field Summary

Fields

Modifier and Type	Field and Description
protected java.util.LinkedList<EpisodeAnalysis>	episodeHistory the saved previous learning episodes
protected int	maxNumSteps The maximum number of learning steps per episode before the agent gives up
protected Model	model The model of the world that is being learned.
protected DynamicProgramming	modelPlanner The valueFunction used on the modeled world to update the value function
protected int	numEpisodesToStore The number of the most recent learning episodes to store.
protected Policy	policy the policy to follow

Fields inherited from class burlap.behavior.singleagent.MDPSolver

actions, debugCode, domain, gamma, hashingFactory, mapToStateIndex, rf, tf

Constructor Summary

Constructors

Constructor and Description
ARTDP(Domain domain, double gamma, HashableStateFactory hashingFactory, double vInit) Initializes using a tabular model of the world and a Boltzmann policy with a fixed temperature of 0.1.
ARTDP(Domain domain, double gamma, HashableStateFactory hashingFactory, Model model, ValueFunctionInitialization vInit) Initializes using the provided model algorithm and a Boltzmann policy with a fixed temperature of 0.1.
ARTDP(Domain domain, double gamma, HashableStateFactory hashingFactory, ValueFunctionInitialization vInit) Initializes using a tabular model of the world and a Boltzmann policy with a fixed temperature of 0.1.

Method Summary

Methods

Modifier and Type	Method and Description
java.util.List<EpisodeAnalysis>	getAllStoredLearningEpisodes()
EpisodeAnalysis	getLastLearningEpisode()
QValue	getQ(State s, AbstractGroundedAction a) Returns the QValue for the given state-action pair.
java.util.List<QValue>	getQs(State s) Returns a List of QValue objects for ever permissible action for the given input state.
void	resetSolver() This method resets all solver results so that a solver can be restarted fresh as if had never solved the MDP.
EpisodeAnalysis	runLearningEpisode(Environment env)
EpisodeAnalysis	runLearningEpisode(Environment env, int maxSteps)
void	setNumEpisodesToStore(int numEps)
void	setPolicy(SolverDerivedPolicy policy) Sets the policy to the provided one.
double	value(State s) Returns the value function evaluation of the given state.

Methods inherited from class burlap.behavior.singleagent.MDPSolver

addNonDomainReferencedAction, getActions, getAllGroundedActions, getDebugCode, getDomain, getGamma, getHashingFactory, getRf, getRF, getTf, getTF, setActions, setDebugCode, setDomain, setGamma, setHashingFactory, setRf, setTf, solverInit, stateHash, toggleDebugPrinting, translateAction

Methods inherited from class java.lang.Object

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

Field Detail

model

protected Model model

The model of the world that is being learned.

modelPlanner

protected DynamicProgramming modelPlanner

The valueFunction used on the modeled world to update the value function

policy

protected Policy policy

the policy to follow

episodeHistory

protected java.util.LinkedList<EpisodeAnalysis> episodeHistory

the saved previous learning episodes

maxNumSteps

protected int maxNumSteps

The maximum number of learning steps per episode before the agent gives up

numEpisodesToStore

protected int numEpisodesToStore

The number of the most recent learning episodes to store.

Constructor Detail

ARTDP

public ARTDP(Domain domain,
     double gamma,
     HashableStateFactory hashingFactory,
     double vInit)

Initializes using a tabular model of the world and a Boltzmann policy with a fixed temperature of 0.1.

Parameters:

domain - the domain

gamma - the discount factor

hashingFactory - the state hashing factory to use for the tabular model and the planning

vInit - the constant value function initialization to use; should be optimisitc.

ARTDP

public ARTDP(Domain domain,
     double gamma,
     HashableStateFactory hashingFactory,
     ValueFunctionInitialization vInit)

Initializes using a tabular model of the world and a Boltzmann policy with a fixed temperature of 0.1.

Parameters:

domain - the domain

gamma - the discount factor

hashingFactory - the state hashing factory to use for the tabular model and the planning

vInit - the value function initialization to use; should be optimisitc.

ARTDP

public ARTDP(Domain domain,
     double gamma,
     HashableStateFactory hashingFactory,
     Model model,
     ValueFunctionInitialization vInit)

Initializes using the provided model algorithm and a Boltzmann policy with a fixed temperature of 0.1.

Parameters:

domain - the domain

gamma - the discount factor

hashingFactory - the state hashing factory to use for the tabular model and the planning

model - the model algorithm to use

vInit - the constant value function initialization to use; should be optimisitc.

Method Detail

setPolicy

public void setPolicy(SolverDerivedPolicy policy)

Sets the policy to the provided one. Should be a policy that operates on a QFunction. Will automatically set its Q-source to this object.

Parameters:

policy - the policy to use.

runLearningEpisode

public EpisodeAnalysis runLearningEpisode(Environment env)

Specified by:

runLearningEpisode in interface LearningAgent

runLearningEpisode

public EpisodeAnalysis runLearningEpisode(Environment env,
                                 int maxSteps)

Specified by:

runLearningEpisode in interface LearningAgent

getLastLearningEpisode

public EpisodeAnalysis getLastLearningEpisode()

setNumEpisodesToStore

public void setNumEpisodesToStore(int numEps)

getAllStoredLearningEpisodes

public java.util.List<EpisodeAnalysis> getAllStoredLearningEpisodes()

getQs

public java.util.List<QValue> getQs(State s)

Description copied from interface: QFunction

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

Specified by:

getQs in interface QFunction

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.

getQ

public QValue getQ(State s,
          AbstractGroundedAction a)

Description copied from interface: QFunction

Returns the QValue for the given state-action pair.

Specified by:

getQ in interface QFunction

Parameters:

s - the input state

a - the input action

Returns:

the QValue for the given state-action pair.

value

public double value(State s)

Description copied from interface: ValueFunction

Returns the value function evaluation of the given state. If the value is not stored, then the default value specified by the ValueFunctionInitialization object of this class is returned.

Specified by:

value in interface ValueFunction

Parameters:

s - the state to evaluate.

Returns:

the value function evaluation of the given state.

resetSolver

public void resetSolver()

Description copied from interface: MDPSolverInterface

This method resets all solver results so that a solver can be restarted fresh as if had never solved the MDP.

Specified by:

resetSolver in interface MDPSolverInterface

Specified by:

resetSolver in class MDPSolver