limited_discrete_action_trainer.py 文件源码

def __init__(
        self,
        normalization_parameters,
        parameters,
    ):
        self._quantile_states = collections.deque(
            maxlen=parameters.action_budget.window_size
        )
        self._quantile = 100 - parameters.action_budget.action_limit
        self.quantile_value = 0
        self._limited_action = np.argmax(
            np.array(parameters.actions) ==
            parameters.action_budget.limited_action
        )
        self._discount_factor = parameters.rl.gamma
        self._quantile_update_rate = \
            parameters.action_budget.quantile_update_rate
        self._quantile_update_frequency = \
            parameters.action_budget.quantile_update_frequency
        self._update_counter = 0
        super(self.__class__,
              self).__init__(normalization_parameters, parameters)
        self._max_q = parameters.rl.maxq_learning