saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-09-16 22:20:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fixes for flake8 6.0 (#1181)

Browse source
This commit is contained in:
Antonin RAFFIN 2022-11-25 15:14:55 +01:00 committed by GitHub
parent 68b190b667
commit cd630a3121
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 6 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
docs/misc/changelog.rst
View file

@ -36,6 +36,7 @@ Deprecations:
Others: Others:
^^^^^^^ ^^^^^^^
- Used issue forms instead of issue templates - Used issue forms instead of issue templates
- Fixed flake8 config to be compatible with flake8 6+
Documentation: Documentation:
^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^

3
setup.cfg
View file

@ -80,7 +80,8 @@ exclude = (?x)(
) )
[flake8] [flake8]
ignore = W503,W504,E203,E231 # line breaks before and after binary operators # line breaks before and after binary operators
ignore = W503,W504,E203,E231
# Ignore import not used when aliases are defined # Ignore import not used when aliases are defined
per-file-ignores = per-file-ignores =
./stable_baselines3/__init__.py:F401 ./stable_baselines3/__init__.py:F401

2
stable_baselines3/common/base_class.py
View file

@ -125,7 +125,7 @@ class BaseAlgorithm(ABC):
# Used for computing fps, it is updated at each call of learn() # Used for computing fps, it is updated at each call of learn()
self._num_timesteps_at_start = 0 self._num_timesteps_at_start = 0
self.seed = seed self.seed = seed
self.action_noise = None # type: Optional[ActionNoise] self.action_noise: Optional[ActionNoise] = None
self.start_time = None self.start_time = None
self.policy = None self.policy = None
self.learning_rate = learning_rate self.learning_rate = learning_rate

4
tests/test_utils.py
View file

@ -298,13 +298,13 @@ def test_evaluate_policy_monitors(vec_env_class):
episode_rewards, episode_lengths = evaluate_policy( episode_rewards, episode_lengths = evaluate_policy(
model, eval_env, n_eval_episodes, return_episode_rewards=True, warn=False model, eval_env, n_eval_episodes, return_episode_rewards=True, warn=False
) )
assert all(map(lambda l: l == 1, episode_lengths)), "AlwaysDoneWrapper did not fix episode lengths to one" assert all(map(lambda length: length == 1, episode_lengths)), "AlwaysDoneWrapper did not fix episode lengths to one"
eval_env.close() eval_env.close()
# Should get longer episodes with with Monitor (true episodes) # Should get longer episodes with with Monitor (true episodes)
eval_env = make_eval_env(with_monitor=True, wrapper_class=AlwaysDoneWrapper) eval_env = make_eval_env(with_monitor=True, wrapper_class=AlwaysDoneWrapper)
episode_rewards, episode_lengths = evaluate_policy(model, eval_env, n_eval_episodes, return_episode_rewards=True) episode_rewards, episode_lengths = evaluate_policy(model, eval_env, n_eval_episodes, return_episode_rewards=True)
assert all(map(lambda l: l > 1, episode_lengths)), "evaluate_policy did not get episode lengths from Monitor" assert all(map(lambda length: length > 1, episode_lengths)), "evaluate_policy did not get episode lengths from Monitor"
eval_env.close() eval_env.close()