saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-05-29 23:07:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Log ppo std

Browse source
This commit is contained in:
Antonin Raffin 2019-10-31 16:17:08 +01:00
parent 72a6f18e43
commit 9644ae89cf
1 changed files with 1 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
torchy_baselines/ppo/ppo.py
View file

@ -253,6 +253,7 @@ class PPO(BaseRLModel):
logger.logkv("entropy", entropy.mean().item())
logger.logkv("policy_loss", policy_loss.item())
logger.logkv("value_loss", value_loss.item())
logger.logkv("std", th.exp(self.policy.log_std).mean().item())
def learn(self, total_timesteps, callback=None, log_interval=1,
eval_env=None, eval_freq=-1, n_eval_episodes=5, tb_log_name="PPO", reset_num_timesteps=True):