burlap.behavior.singleagent.learning.actorcritic

Interface Critic

All Known Implementing Classes:

TDLambda, TimeIndexedTDLambda

public interface Critic

This interface provides the methods necessary for implementing the critic part of an actor-critic learning algorithm. The critic is responsible for observing behavior (state, action, state tuples) and returning a critique of that behavior. Typically, Critic objects will need to take as input a reward function to judge this behavior.

Author:

James MacGlashan

Method Summary

Methods

Modifier and Type	Method and Description
void	addNonDomainReferencedAction(Action a) This method allows the critic to critique actions that are not apart of the domain definition.
CritiqueResult	critiqueAndUpdate(State s, GroundedAction ga, State sprime) This method's implementation provides the critique for some specific instance of the behavior.
void	endEpisode() This method is called whenever a learning episode terminates
void	initializeEpisode(State s) This method is called whenever a new learning episode begins
void	resetData() Used to reset any data that was created/modified during learning so that learning can be begin anew.

Method Detail

addNonDomainReferencedAction

void addNonDomainReferencedAction(Action a)

This method allows the critic to critique actions that are not apart of the domain definition.

Parameters:

a - a an action not apart of the of the domain definition that this critic should be able to crique.

initializeEpisode

void initializeEpisode(State s)

This method is called whenever a new learning episode begins

Parameters:

s - the initial state of the new learning episode

endEpisode

void endEpisode()

This method is called whenever a learning episode terminates

critiqueAndUpdate

CritiqueResult critiqueAndUpdate(State s,
                               GroundedAction ga,
                               State sprime)

This method's implementation provides the critique for some specific instance of the behavior.

Parameters:

s - an input state

ga - an action taken in s

sprime - the state the agent transitioned to for taking action ga in state s

Returns:

the critique of this behavior.

resetData

void resetData()

Used to reset any data that was created/modified during learning so that learning can be begin anew.