How to monitor the episode/epoch return/length in Tianshou?

[PingH129]

• I have marked all applicable categories:
  • exception-raising bug
  • RL algorithm bug
  • documentation request (i.e. "X is missing from the documentation.")
  • new feature request
  • design request (i.e. "X should be changed to Y.")
• [+] I have visited the source website
• [+] I have searched through the issue tracker for duplicates
• [+] I have mentioned version numbers, operating system and environment, where applicable:

  import tianshou, gymnasium as gym, torch, numpy, sys
  print(tianshou.__version__, gym.__version__, torch.__version__, numpy.__version__, sys.version, sys.platform)

I'm using the trainer in Tianshou for MARL, but how can I monitor the episode/epoch return and length in tianshou in the training process?

[Trinkle23897]

You should check the collector's return value. It has episodic statistic number. For example:

tianshou/tianshou/data/collector.py

Lines 574 to 581 in 5bf923c

	return CollectStats.with_autogenerated_stats(
	returns=np.array(episode_returns),
	lens=np.array(episode_lens),
	n_collected_episodes=num_collected_episodes,
	n_collected_steps=step_count,
	collect_time=collect_time,
	collect_speed=step_count / collect_time,
	)