PLE_env.py 文件源码

def act(self, action):
        action = self._actions[action]

        reward = 0
        for _ in range(self._frame_skip):
            reward += self._ple.act(action)
            if self.inTerminalState():
                break

        self._screen = self._ple.getScreenGrayscale()
        cv2.resize(self._screen, (48, 48), self._reduced_screen, interpolation=cv2.INTER_NEAREST)

        self._mode_score += reward
        return np.sign(reward)