valueIterationAgents.py 文件源码

def __init__(self, mdp, discount = 0.9, iterations = 100):
        """
          Your value iteration agent should take an mdp on
          construction, run the indicated number of iterations
          and then act according to the resulting policy.

          Some useful mdp methods you will use:
              mdp.getStates()
              mdp.getPossibleActions(state)
              mdp.getTransitionStatesAndProbs(state, action)
              mdp.getReward(state, action, nextState)
              mdp.isTerminal(state)
        """
        self.mdp = mdp
        self.discount = discount
        self.iterations = iterations
        self.values = util.Counter() # A Counter is a dict with default 0
        self.actions = {}

        for _ in range(iterations):
            new_stateValues = {}
            new_actionValue = {}
            for state in self.mdp.getStates():
                qvalue_list = []
                possible_actions = mdp.getPossibleActions(state)
                if (len(possible_actions) == 0):
                    new_stateValues[state] = 0                 
                    new_actionValue[state] = None
                else:
                    for action in possible_actions:
                        qvalue_list.append((self.getQValue(state,action),action))
                    vvalue = max(qvalue_list)
                    new_stateValues[state] = vvalue[0]                   
                    new_actionValue[state] = vvalue[1]

            self.values = new_stateValues     
            self.actions = new_actionValue