Package org.tweetyproject.machinelearning.rl.mdp.algorithms

Class IterativePolicyEvaluation<S extends State,A extends Action>

java.lang.Object

org.tweetyproject.machinelearning.rl.mdp.algorithms.IterativePolicyEvaluation<S,A>

Type Parameters:

S - The type of states

A - The type of actions

All Implemented Interfaces:

PolicyEvaluation<S,A>

public class IterativePolicyEvaluation<S extends State,A extends Action>
extends Object
implements PolicyEvaluation<S,A>

Determines utilities iteratively.

Author:

Matthias Thimm

Constructor Summary

Constructors

Constructor	Description
IterativePolicyEvaluation(long num_iterations)	Creates a new policy evaluation algorithm

Method Summary

Modifier and Type	Method	Description
Map<S,Double>	getUtilities(MarkovDecisionProcess<S,A> mdp, Policy<S,A> pi, double gamma)	Determines the utilities of the states in the MDP wrt.

Methods inherited from class java.lang.Object

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

Constructor Details

IterativePolicyEvaluation

public IterativePolicyEvaluation(long num_iterations)

Creates a new policy evaluation algorithm

Parameters:

num_iterations - the given number of num_iterations

Method Details

getUtilities

public Map<S,Double> getUtilities(MarkovDecisionProcess<S,A> mdp,
 Policy<S,A> pi,
 double gamma)

Description copied from interface: PolicyEvaluation

Determines the utilities of the states in the MDP wrt. the given policy.

Specified by:

getUtilities in interface PolicyEvaluation<S extends State,A extends Action>

Parameters:

mdp - some MDP

pi - some policy

gamma - the discount factor

Returns:

the utilities of the states of the MDP.