aima.core.probability.example

Class MDPFactory

java.lang.Object

aima.core.probability.example.MDPFactory

public class MDPFactory
extends java.lang.Object

Author:

Ciaran O'Reilly, Ravi Mohan

Constructor Summary

Constructors

Constructor and Description
MDPFactory()

Method Summary

Modifier and Type	Method and Description
static ActionsFunction<Cell<java.lang.Double>,CellWorldAction>	createActionsFunctionForFigure17_1(CellWorld<java.lang.Double> cw) Returns the allowed actions from a specified cell within the cell world described in Fig 17.1.
static MarkovDecisionProcess<Cell<java.lang.Double>,CellWorldAction>	createMDPForFigure17_3(CellWorld<java.lang.Double> cw) Constructs an MDP that can be used to generate the utility values detailed in Fig 17.3.
static RewardFunction<Cell<java.lang.Double>>	createRewardFunctionForFigure17_1()
static TransitionProbabilityFunction<Cell<java.lang.Double>,CellWorldAction>	createTransitionProbabilityFunctionForFigure17_1(CellWorld<java.lang.Double> cw) Figure 17.1 (b) Illustration of the transition model of the environment: the 'intended' outcome occurs with probability 0.8, but with probability 0.2 the agent moves at right angles to the intended direction.

Methods inherited from class java.lang.Object

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

Constructor Detail

MDPFactory

public MDPFactory()

Method Detail

createMDPForFigure17_3

public static MarkovDecisionProcess<Cell<java.lang.Double>,CellWorldAction> createMDPForFigure17_3(CellWorld<java.lang.Double> cw)

Constructs an MDP that can be used to generate the utility values detailed in Fig 17.3.

Parameters:

cw - the cell world from figure 17.1.

Returns:

an MDP that can be used to generate the utility values detailed in Fig 17.3.

createActionsFunctionForFigure17_1

public static ActionsFunction<Cell<java.lang.Double>,CellWorldAction> createActionsFunctionForFigure17_1(CellWorld<java.lang.Double> cw)

Returns the allowed actions from a specified cell within the cell world described in Fig 17.1.

Parameters:

cw - the cell world from figure 17.1.

Returns:

the set of actions allowed at a particular cell. This set will be empty if at a terminal state.

createTransitionProbabilityFunctionForFigure17_1

public static TransitionProbabilityFunction<Cell<java.lang.Double>,CellWorldAction> createTransitionProbabilityFunctionForFigure17_1(CellWorld<java.lang.Double> cw)

Figure 17.1 (b) Illustration of the transition model of the environment: the 'intended' outcome occurs with probability 0.8, but with probability 0.2 the agent moves at right angles to the intended direction. A collision with a wall results in no movement.

Parameters:

cw - the cell world from figure 17.1.

Returns:

the transition probability function as described in figure 17.1.

createRewardFunctionForFigure17_1

public static RewardFunction<Cell<java.lang.Double>> createRewardFunctionForFigure17_1()

Returns:

the reward function which takes the content of the cell as being the reward value.