aima.core.probability.mdp.PolicyEvaluation Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of aima-core Show documentation

AIMA-Java Core Algorithms from the book Artificial Intelligence a Modern Approach 3rd Ed.

There is a newer version: 3.0.0

package aima.core.probability.mdp;

import java.util.Map;

import aima.core.agent.Action;

/**
 * Artificial Intelligence A Modern Approach (3rd Edition): page 656.

 * 

 * Given a policy π_i, calculate
 * U_i=U^π_i, the utility of each state if
 * π_i were to be executed.
 * 
 * @param 
 *            the state type.
 * @param 
 *            the action type.
 * 
 * @author Ciaran O'Reilly
 * @author Ravi Mohan
 */
public interface PolicyEvaluation {
	/**
	 * Policy evaluation: given a policy π_i, calculate
	 * U_i=U^π_i, the utility of each state if
	 * π_i were to be executed.
	 * 
	 * @param pi_i
	 *            a policy vector indexed by state
	 * @param U
	 *            a vector of utilities for states in S
	 * @param mdp
	 *            an MDP with states S, actions A(s), transition model P(s'|s,a)
	 * @return U_i=U^π_i, the utility of each
	 *         state if π_i were to be executed.
	 */
	Map evaluate(Map pi_i, Map U,
			MarkovDecisionProcess mdp);
}