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 πi, calculate
* Ui=Uπi, the utility of each state if
* πi 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 πi, calculate
* Ui=Uπi, the utility of each state if
* πi 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 Ui=Uπi, the utility of each
* state if πi were to be executed.
*/
Map evaluate(Map pi_i, Map U,
MarkovDecisionProcess mdp);
}