burlap.behavior.stochasticgames.madynamicprogramming

Class MADynamicProgramming.JointActionTransitions

java.lang.Object

burlap.behavior.stochasticgames.madynamicprogramming.MADynamicProgramming.JointActionTransitions

Enclosing class:

MADynamicProgramming

public class MADynamicProgramming.JointActionTransitions
extends java.lang.Object

A class for holding all of the transition dynamic information for a given joint action in a given state. This includes state transitions as well as joint rewards. Information is stored as a triple consisting of the JointAction, the list of state transtitions (StateTransitionProb objects), and a list of joint rewards (A map from agent names to rewards received).

Author:

James MacGlashan

Field Summary

Fields

Modifier and Type	Field and Description
JointAction	ja
java.util.List<double[]>	jrs
java.util.List<StateTransitionProb>	tps

Constructor Summary

Constructors

Constructor and Description
JointActionTransitions(State s, JointAction ja) Generates the transition information for the given state and joint aciton

Method Summary

Methods inherited from class java.lang.Object

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

Field Detail

ja

public JointAction ja

tps

public java.util.List<StateTransitionProb> tps

jrs

public java.util.List<double[]> jrs

Constructor Detail

JointActionTransitions

public JointActionTransitions(State s,
                              JointAction ja)

Generates the transition information for the given state and joint aciton

Parameters:

s - the state in which the joint action is applied

ja - the joint action applied to the given state