models.py 文件源码

def compile(self, state_dim_values, lr=0.2, policy_rule="maxrand", init_value=None):
        """Build and initialize table with all possible state values.
           state_dim_values consists of a tuple of arrays or lists - each array
           gives every possible value for the corresponding dimension.
        """

        self.policy_rule = policies.get(policy_rule)

        if init_value is None:
            self.init_value = np.zeros(self.num_actions)
        else:
            self.init_value = init_value

        self.table = {key: np.array(self.init_value) for key in list(itertools.product(*state_dim_values))}
        self.lr = lr