dqn_utils.py 文件源码

def store_effect(self, idx, action, reward, done):
        """Store effects of action taken after obeserving frame stored
        at index idx. The reason `store_frame` and `store_effect` is broken
        up into two functions is so that once can call `encode_recent_observation`
        in between.

        Paramters
        ---------
        idx: int
            Index in buffer of recently observed frame (returned by `store_frame`).
        action: int
            Action that was performed upon observing this frame.
        reward: float
            Reward that was received when the actions was performed.
        done: bool
            True if episode was finished after performing that action.
        """
        self.action[idx] = action
        self.reward[idx] = reward
        self.done[idx]   = done