Skip to content

Instantly share code, notes, and snippets.

@ceteri
Last active Jul 7, 2020
Embed
What would you like to do?
N_ITER = 40
s = "{:3d} reward {:6.2f}/{:6.2f}/{:6.2f} len {:6.2f} saved {}"
for n in range(N_ITER):
result = agent.train()
file_name = agent.save(CHECKPOINT_ROOT)
print(s.format(
n + 1,
result["episode_reward_min"],
result["episode_reward_mean"],
result["episode_reward_max"],
result["episode_len_mean"],
file_name
))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment