saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-28 20:11:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Limit CMAES to one episode

Browse source
This commit is contained in:
Antonin RAFFIN 2020-08-11 11:43:12 +02:00
parent b66104c3ce
commit f46b5ef619
1 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
stable_baselines3/cmaes/cmaes.py
View file

@ -24,7 +24,7 @@ class CMAES(BaseAlgorithm):
std_init: float = 0.5,
best_individual: Union[np.ndarray, None, str] = None,
diagonal_cov: bool = False,
max_hist: int = 10,
max_hist: int = 100,
pop_size: Optional[int] = None,
policy_kwargs: Dict[str, Any] = None,
tensorboard_log: Optional[str] = None,
@ -157,7 +157,14 @@ class CMAES(BaseAlgorithm):
candidate_steps += 1
self._update_current_progress_remaining(self.num_timesteps, self._total_timesteps)
if candidate_steps > self.n_steps:
if done:
self._episode_num += 1
# Log training infos
if log_interval is not None and self._episode_num % log_interval == 0:
self._dump_logs()
if candidate_steps > self.n_steps or done:
if self.verbose > 0:
print(f"Candidate {candidate_idx + 1}, return={returns[candidate_idx]:.2f}")
# force reset
@ -169,12 +176,6 @@ class CMAES(BaseAlgorithm):
else:
break
if done:
self._episode_num += 1
# Log training infos
if log_interval is not None and self._episode_num % log_interval == 0:
self._dump_logs()
callback.on_rollout_end()