saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-09-15 22:10:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Save last mean reward

Browse source
This commit is contained in:
Antonin Raffin 2020-02-11 13:22:44 +01:00
parent 75a86881b3
commit 8eb82c86e3
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
torchy_baselines/common/callbacks.py
View file

@ -232,6 +232,7 @@ class EvalCallback(EventCallback):
self.n_eval_episodes = n_eval_episodes self.n_eval_episodes = n_eval_episodes
self.eval_freq = eval_freq self.eval_freq = eval_freq
self.best_mean_reward = -np.inf self.best_mean_reward = -np.inf
self.last_mean_reward = -np.inf
self.deterministic = deterministic self.deterministic = deterministic
self.render = render self.render = render
@ -280,6 +281,7 @@ class EvalCallback(EventCallback):
mean_reward, std_reward = np.mean(episode_rewards), np.std(episode_rewards) mean_reward, std_reward = np.mean(episode_rewards), np.std(episode_rewards)
mean_ep_length, std_ep_length = np.mean(episode_lengths), np.std(episode_lengths) mean_ep_length, std_ep_length = np.mean(episode_lengths), np.std(episode_lengths)
self.last_mean_reward = mean_reward
if self.verbose > 0: if self.verbose > 0:
print(f"Eval num_timesteps={self.num_timesteps}, " print(f"Eval num_timesteps={self.num_timesteps}, "