A C M N P R S T U V

A

actionName - Variable in class Mdp

an array containing the names of all of the actions

animate(int[], int) - Method in class CatMouseAnimator

This method will animate the mdp provided to the constructor for numSteps steps, following policy pi.

C

CatMouse - class CatMouse.

This class provides a simple main for running on cat and mouse data.

CatMouse() - Constructor for class CatMouse

CatMouseAnimator - class CatMouseAnimator.

This class can be used to "animate" the interaction between a cat and mouse.

CatMouseAnimator(Mdp) - Constructor for class CatMouseAnimator

The constructor for this class for printing results to standard output.

CatMouseAnimator(Mdp, PrintStream) - Constructor for class CatMouseAnimator

The constructor for this class for printing results to a given print stream.

M

Mdp - class Mdp.

This class represents an MDP, and includes a constructor that can read the MDP from a data file.

Mdp(String) - Constructor for class Mdp

This constructor reads in data from filename and sets up all of the public fields.

main(String[]) - Static method in class CatMouse

This is a simple main.

N

nextState - Variable in class Mdp

a list of the possible states that can be reached from each state under each action

numActions - Variable in class Mdp

total number of actions

numStates - Variable in class Mdp

total number of states

P

PolicyEval - class PolicyEval.

This is the template of a class that evaluates a given policy, i.e., computes the utility of each state when actions are chosen according to it.

PolicyEval(Mdp, double, int[]) - Constructor for class PolicyEval

The constructor for this class.

PolicyIter - class PolicyIter.

This is the template of a class that should run policy iteration on a given MDP to compute the optimal policy which is returned in the public policy field.

PolicyIter(Mdp, double) - Constructor for class PolicyIter

The constructor for this class.

policy - Variable in class PolicyIter

the computed optimal policy for the given MDP

policy - Variable in class ValueIter

the computed optimal policy for the given MDP

precision - Static variable in class PolicyEval

the precision used to determine when to stop iterating (called epsilon in lecture)

precision - Static variable in class ValueIter

the precision used to determine when to stop iterating (called epsilon in lecture)

R

reward - Variable in class Mdp

an array containing the (immediate) reward associated with every state

S

startState - Variable in class Mdp

the start state

stateName - Variable in class Mdp

an array containing the names of all of the states

T

transProb - Variable in class Mdp

a table of transition probabilities: transProb[s][a][i] is the probability of transitioning from state s under action a to state nextState[s][a][i].

U

utility - Variable in class PolicyEval

the computed utility of each state under the given policy

utility - Variable in class ValueIter

the computed optimal utility for the given MDP

V

ValueIter - class ValueIter.

This is the template of a class that should run value iteration on a given MDP to compute the optimal policy which is returned in the public policy field.

ValueIter(Mdp, double) - Constructor for class ValueIter

The constructor for this class.

A C M N P R S T U V