Skip to content
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

[gym] Enable multi-GPU support with PPO when mirror_mat are defined #774

Merged
merged 1 commit into from
Apr 27, 2024

Conversation

mwulfman
Copy link
Contributor

Closes #773

@duburcqa
Copy link
Owner

duburcqa commented Apr 23, 2024

You broke something else by trying to fix your bug. I suggest to keep the output of train as it is currently, but fix typing and doc, then adapt the other parts that assumes it returns the checkpoint path.

@mwulfman mwulfman changed the title [gym] Broken RLlib utilities with ray >= 2.9 [gym] Fix typing and docs RLlib utilities with ray >= 2.9 Apr 24, 2024
@mwulfman mwulfman force-pushed the fix-rllib-utilities branch from a9ac060 to 3cdc6a6 Compare April 27, 2024 16:35
@mwulfman mwulfman changed the title [gym] Fix typing and docs RLlib utilities with ray >= 2.9 [gym] Enable multi-GPU support with PPO when mirror_mat are defined Apr 27, 2024
@duburcqa duburcqa merged commit 91c94ed into duburcqa:dev Apr 27, 2024
16 of 28 checks passed
@duburcqa duburcqa mentioned this pull request Apr 28, 2024
duburcqa added a commit that referenced this pull request Apr 28, 2024
* [core] Full support of serialization of 'Robot'. (#770) (#775) 
* [core] Do NOT use 'enable_shared_from_this' if not strictly necessary. (#775) 
* [core] Rename macro 'PRINT_WARNING' in 'JIMINY_WARNING' to avoid conflicts. (#775) 
* [python/simulator] 'plot' now support multi-robot simulations. (#770)
* [gym/common] Speedup 'PDController' env pipeline block. (#770)
* [gym/common] Speedup 'StackedJiminyEnv' wrapper. (#770)
* [gym/common] More generic 'FilterObservation', 'StackedJiminyEnv' wrappers.  (#770) (#776)
* [gym/common] Improve 'render_mode' support.
* [gym/zoo] Cleanup and speedup toy model environments. (#770)
* [gym/rllib] Fix multi-GPU support using custom PPO (#774)
* [gym/rllib] Fix 'train' method typing and documentation. (#775) 
* [misc] Fix partially broken 'mypy' static type checking for 'jiminy_py' module. (#770)
* [misc] Add RL tutorial notebook.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[gym] Fix typing and docs RLlib utilities with ray >= 2.9
2 participants