src/algos/no_episodic_counts.py [340:382]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            'scheduler_state_dict': scheduler.state_dict(),
            'flags': vars(flags),
        }, checkpointpath)

    timer = timeit.default_timer
    try:
        last_checkpoint_time = timer()
        while frames < flags.total_frames:
            start_frames = frames
            start_time = timer()
            time.sleep(5)

            if timer() - last_checkpoint_time > flags.save_interval * 60: 
                checkpoint(frames)
                last_checkpoint_time = timer()

            fps = (frames - start_frames) / (timer() - start_time)
            
            if stats.get('episode_returns', None):
                mean_return = 'Return per episode: %.1f. ' % stats[
                    'mean_episode_return']
            else:
                mean_return = ''

            total_loss = stats.get('total_loss', float('inf'))
            if stats:
                log.info('After %i frames: loss %f @ %.1f fps. Mean Return %.1f. \n Stats \n %s', \
                        frames, total_loss, fps, stats['mean_episode_return'], pprint.pformat(stats))

    except KeyboardInterrupt:
        return  
    else:
        for thread in threads:
            thread.join()
        log.info('Learning finished after %d frames.', frames)
    finally:
        for _ in range(flags.num_actors):
            free_queue.put(None)
        for actor in actor_processes:
            actor.join(timeout=1)

    checkpoint(frames)
    plogger.close()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/algos/rnd.py [305:347]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            'scheduler_state_dict': scheduler.state_dict(),
            'flags': vars(flags),
        }, checkpointpath)

    timer = timeit.default_timer
    try:
        last_checkpoint_time = timer()
        while frames < flags.total_frames:
            start_frames = frames
            start_time = timer()
            time.sleep(5)

            if timer() - last_checkpoint_time > flags.save_interval * 60:  
                checkpoint(frames)
                last_checkpoint_time = timer()

            fps = (frames - start_frames) / (timer() - start_time)
            
            if stats.get('episode_returns', None):
                mean_return = 'Return per episode: %.1f. ' % stats[
                    'mean_episode_return']
            else:
                mean_return = ''

            total_loss = stats.get('total_loss', float('inf'))
            if stats:
                log.info('After %i frames: loss %f @ %.1f fps. Mean Return %.1f. \n Stats \n %s', \
                        frames, total_loss, fps, stats['mean_episode_return'], pprint.pformat(stats))

    except KeyboardInterrupt:
        return  
    else:
        for thread in threads:
            thread.join()
        log.info('Learning finished after %d frames.', frames)
    finally:
        for _ in range(flags.num_actors):
            free_queue.put(None)
        for actor in actor_processes:
            actor.join(timeout=1)

    checkpoint(frames)
    plogger.close()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -