def _sample()

in replay_buffer.py [0:0]

• 18 lines of code
• 3 McCabe index (conditional complexity)

    def _sample(self):
        try:
            self._try_fetch()
        except:
            traceback.print_exc()
        self._samples_since_last_fetch += 1
        episode = self._sample_episode()
        # add +1 for the first dummy transition
        idx = np.random.randint(0, episode_len(episode) - self._nstep + 1) + 1
        obs = episode['observation'][idx - 1]
        action = episode['action'][idx]
        next_obs = episode['observation'][idx + self._nstep - 1]
        reward = np.zeros_like(episode['reward'][idx])
        discount = np.ones_like(episode['discount'][idx])
        for i in range(self._nstep):
            step_reward = episode['reward'][idx + i]
            reward += discount * step_reward
            discount *= episode['discount'][idx + i] * self._discount
        return (obs, action, reward, discount, next_obs)