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)
    """
    self.mdp = mdp
    self.discount = discount
    self.iterations = iterations
    self.values = util.Counter() # A Counter is a dict with default 0

    "*** YOUR CODE HERE ***"