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

Removing dead code for handling time limits (#831)

Browse source 
* Removing dead code for handling time limits (see #829)

* Mentionning remove_time_limit_termination in the changelog

* Update changelog.rst

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
This commit is contained in:
Grégoire Passault 2022-03-23 08:33:55 -04:00 committed by GitHub
parent 009bb0549a
commit 00ac43b0a9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/misc/changelog.rst
View file

@ -40,6 +40,7 @@ Deprecations:
Others:
^^^^^^^
- Fixed pytest warnings
- Removed parameter ``remove_time_limit_termination`` in off policy algorithms since it was dead code (@Gregwar)
Documentation:
^^^^^^^^^^^^^^
@ -928,3 +929,4 @@ And all the contributors:
@wkirgsn @AechPro @CUN-bjy @batu @IljaAvadiev @timokau @kachayev @cleversonahum
@eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92 @thomasgubler @IperGiove @ScheiklP
@simoninithomas @armandpl @manuel-delverme @Gautam-J @gianlucadecola @buoyancy99 @caburu @xy9485
@Gregwar

7
stable_baselines3/common/off_policy_algorithm.py
View file

@ -69,8 +69,6 @@ class OffPolicyAlgorithm(BaseAlgorithm):
:param use_sde_at_warmup: Whether to use gSDE instead of uniform sampling
during the warm up phase (before learning starts)
:param sde_support: Whether the model support gSDE or not
:param remove_time_limit_termination: Remove terminations (dones) that are due to time limit.
See https://github.com/hill-a/stable-baselines/issues/863
:param supported_action_spaces: The action spaces supported by the algorithm.
"""
@ -103,7 +101,6 @@ class OffPolicyAlgorithm(BaseAlgorithm):
sde_sample_freq: int = -1,
use_sde_at_warmup: bool = False,
sde_support: bool = True,
remove_time_limit_termination: bool = False,
supported_action_spaces: Optional[Tuple[gym.spaces.Space, ...]] = None,
):
@ -138,10 +135,6 @@ class OffPolicyAlgorithm(BaseAlgorithm):
self.replay_buffer_kwargs = replay_buffer_kwargs
self._episode_storage = None
# Remove terminations (dones) that are due to time limit
# see https://github.com/hill-a/stable-baselines/issues/863
self.remove_time_limit_termination = remove_time_limit_termination
# Save train freq parameter, will be converted later to TrainFreq object
self.train_freq = train_freq