stable-baselines3/stable_baselines3/common
Timo Kaufmann 09e9fc42eb
Use consistent logging keys (#605)
* Use a consistent key to log the total timesteps

This changes the timestep logging key of on-policy algorithms from
`time/total_timesteps` to `time/total timesteps` (note the
underscore/space). The off-policy algorithms and the eval callback
already use the latter, so this behavior is more consistent.

* Use underscores instead of spaces in logging keys

Most keys already followed this policy and consistent behavior is
friendlier to new users.

* Minor edit and bump version

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
2021-10-12 13:17:30 +02:00
..
envs Add method predict_values for ActorCriticPolicy (#569) 2021-09-15 14:03:04 +02:00
sb2_compat Add callable signatures to type annotations. (#215) 2020-11-15 17:50:28 +01:00
vec_env VecNormalize: allow non-continuous observations when norm_obs is False (#575) 2021-09-18 12:11:01 +02:00
__init__.py Update docs (custom policy, type hints) (#167) 2020-09-29 20:41:14 +03:00
atari_wrappers.py Add SUMO-RL as example project in the docs (#257) 2020-12-13 17:15:45 +01:00
base_class.py Doc fix and improve error messages (#598) 2021-10-08 18:08:31 +02:00
buffers.py Corrected DictReplayBuffer observation dtype #484 (#486) 2021-06-22 13:41:26 +02:00
callbacks.py Use consistent logging keys (#605) 2021-10-12 13:17:30 +02:00
distributions.py KL Divergence Helper Function (#431) 2021-05-20 19:01:07 +02:00
env_checker.py Dictionary Observations (#243) 2021-05-11 12:29:30 +02:00
env_util.py Added wrapper_kwargs argument to make_vec_env (#448) 2021-05-23 11:33:34 +02:00
evaluation.py Added support for vector envs in evaluation (#447) 2021-05-28 12:40:29 +02:00
logger.py Fix logger setup (#469) 2021-06-14 15:17:48 +02:00
monitor.py Fix type annotations (#522) 2021-07-29 13:02:09 +02:00
noise.py Improve typing coverage (#175) 2020-10-07 10:51:49 +02:00
off_policy_algorithm.py Use consistent logging keys (#605) 2021-10-12 13:17:30 +02:00
on_policy_algorithm.py Avoid putting target networks into training mode (#553) 2021-08-30 17:42:41 +02:00
policies.py Remove sde_net_arch + Simplify policy (#584) 2021-09-28 22:32:54 +03:00
preprocessing.py Documentation update (#450) 2021-05-23 13:13:11 +02:00
results_plotter.py Fix default arguments + add bugbear (#363) 2021-03-25 11:35:21 +02:00
running_mean_std.py Cleanup docstring types (#169) 2020-10-02 20:05:55 +03:00
save_util.py Fix type annotations (#522) 2021-07-29 13:02:09 +02:00
torch_layers.py Remove sde_net_arch + Simplify policy (#584) 2021-09-28 22:32:54 +03:00
type_aliases.py Dictionary Observations (#243) 2021-05-11 12:29:30 +02:00
utils.py Fixes in is_vectorized_observation (#587) 2021-09-28 21:57:49 +02:00