burlap.mdp.singleagent.environment

Class EnvironmentOutcome

java.lang.Object

burlap.mdp.singleagent.environment.EnvironmentOutcome

Direct Known Subclasses:

EnvironmentOptionOutcome

public class EnvironmentOutcome
extends java.lang.Object

A tuple for specifying the outcome of executing an action in an Environment. The class consists of the previous environment observation (as a State) in which the action was taken; the action taken (as a Action); the next environment observation (also a State following the action; the reward received from the environment; and whether the new state of the environment is a terminal state.

Author:

James MacGlashan.

Field Summary

Fields

Modifier and Type	Field and Description
Action	a The action taken in the environment
State	o The previous environment observation (as a State when the action was taken.
State	op The next environment observation (as a State) following the action's execution.
double	r The reward received
boolean	terminated Whether the next state to which the environment transitioned is a terminal state (true if so, false otherwise)

Constructor Summary

Constructors

Constructor and Description
EnvironmentOutcome(State o, Action a, State op, double r, boolean terminated) Initializes.

Method Summary

Methods inherited from class java.lang.Object

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

Field Detail

o

public State o

The previous environment observation (as a State when the action was taken.

a

public Action a

The action taken in the environment

op

public State op

The next environment observation (as a State) following the action's execution.

r

public double r

The reward received

terminated

public boolean terminated

Whether the next state to which the environment transitioned is a terminal state (true if so, false otherwise)

Constructor Detail

EnvironmentOutcome

public EnvironmentOutcome(State o,
                          Action a,
                          State op,
                          double r,
                          boolean terminated)

Initializes.

Parameters:

o - The previous state of the environment when the action was taken.

a - The action taken in the environment

op - The next state to which the environment transitioned

r - The reward received

terminated - Whether the next state to which the environment transitioned is a terminal state (true if so, false otherwise)