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

Class PolicyIteration<S extends State,A extends Action>

java.lang.Object

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

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

Type Parameters:

S - The type of states

A - The type of actions

public class PolicyIteration<S extends State,A extends Action>
extends OfflineAlgorithm<S,A>

The policy iteration algorithm for determining optimal policies

Author:

Matthias Thimm

Constructor Summary

Constructors

Constructor	Description
PolicyIteration(PolicyEvaluation<S,A> pe)	Creates a new instance of the policy iteration algorithm, which uses the given policy evaluation algorithm.

Method Summary

Modifier and Type	Method	Description
Policy<S,A>	getPolicy(MarkovDecisionProcess<S,A> mdp, double gamma)	Determines the optimal policy for the given MDP.

Methods inherited from class org.tweetyproject.machinelearning.rl.mdp.algorithms.OfflineAlgorithm

getPolicy

Methods inherited from class java.lang.Object

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

Constructor Details

PolicyIteration

public PolicyIteration(PolicyEvaluation<S,A> pe)

Creates a new instance of the policy iteration algorithm, which uses the given policy evaluation algorithm.

Parameters:

pe - some policy evaluation algorithm.

Method Details

getPolicy

public Policy<S,A> getPolicy(MarkovDecisionProcess<S,A> mdp,
 double gamma)

Description copied from class: OfflineAlgorithm

Determines the optimal policy for the given MDP.

Specified by:

getPolicy in class OfflineAlgorithm<S extends State,A extends Action>

Parameters:

mdp - some MDP

gamma - the used discount factor for utility determination

Returns:

the optimal policy