-
Notifications
You must be signed in to change notification settings - Fork 100
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
improve gym speedup #210
Merged
Merged
improve gym speedup #210
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@wangsiping97 please do the rest the same as my commit |
TODO:
|
Trinkle23897
approved these changes
Nov 1, 2022
3 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Improved speedup in gym by:
max_episode_steps
into the base config in c++max_episode_steps
from c++ default config per env intoregistration.py
trunc
computation logics from python to c++This PR also includes a big refactor of calling test env. We use
make_dm
/make_gym
instead ofenvpool_cls(spec_cls(spec_cls.gen_config(...)))
.Motivation and Context
The computation of
trunc
ingym_envpool.py
is shown as a bottleneck bypy-spy
.After fix, envpool's speedup in gym improved from ~1.0x to ~1.3x (using make_gym instead of make_dm for the test below):
Types of changes
What types of changes does your code introduce? Put an
x
in all the boxes that apply:Implemented Tasks
max_episode_steps
from c++ default config per env intoregistration.py
trunc
computation logics from python to c++max_episode_steps
in test filesChecklist
Go over all the following points, and put an
x
in all the boxes that apply.If you are unsure about any of these, don't hesitate to ask. We are here to help!
make format
(required)make lint
(required)make bazel-test
pass. (required)