with common.RewardTracker(writer, np.inf, group_rewards=100) as reward_tracker:
    while True:
        step_idx += 1
        buffer.populate(1)
        selector.epsilon = max(EPSILON_STOP, EPSILON_START - step_idx / EPSILON_STEPS)

        new_rewards = exp_source.pop_rewards_steps()
        if new_rewards:
            reward_tracker.reward(new_rewards[0], step_idx, selector.epsilon)

• 只需要有__enter__方法，__exit__方法就行了，

class RewardTracker:
    def __init__(self, writer, stop_reward, group_rewards=1):
        self.writer = writer
        self.stop_reward = stop_reward
        self.reward_buf = []
        self.steps_buf = []
        self.group_rewards = group_rewards

    def __enter__(self):
        self.ts = time.time()
        self.ts_frame = 0
        self.total_rewards = []
        self.total_steps = []
        return self

    def __exit__(self, *args):
        self.writer.close()

    def reward(self, reward_steps, frame, epsilon=None):
        reward, steps = reward_steps
        self.reward_buf.append(reward)
        self.steps_buf.append(steps)
        if len(self.reward_buf) < self.group_rewards:
            return False
        reward = np.mean(self.reward_buf)
        steps = np.mean(self.steps_buf)
        self.reward_buf.clear()
        self.steps_buf.clear()
        self.total_rewards.append(reward)
        self.total_steps.append(steps)
        speed = (frame - self.ts_frame) / (time.time() - self.ts)
        self.ts_frame = frame
        self.ts = time.time()
        mean_reward = np.mean(self.total_rewards[-100:])
        mean_steps = np.mean(self.total_steps[-100:])
        epsilon_str = "" if epsilon is None else ", eps %.2f" % epsilon
        print("%d: done %d games, mean reward %.3f, mean steps %.2f, speed %.2f f/s%s" % (
            frame, len(self.total_rewards)*self.group_rewards, mean_reward, mean_steps, speed, epsilon_str
        ))
        sys.stdout.flush()
        if epsilon is not None:
            self.writer.add_scalar("epsilon", epsilon, frame)
        self.writer.add_scalar("speed", speed, frame)
        self.writer.add_scalar("reward_100", mean_reward, frame)
        self.writer.add_scalar("reward", reward, frame)
        self.writer.add_scalar("steps_100", mean_steps, frame)
        self.writer.add_scalar("steps", steps, frame)
        if mean_reward > self.stop_reward:
            print("Solved in %d frames!" % frame)
            return True
        return False