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
MADDPG implementation in RLlib #5348
Conversation
…ch as input for SyncReplayOptimizer. 2. Add `synchronize_sampling` argument to `SyncReplayOptimizer.__init__`, which is necessary for centralized critic training.
…ch as input for SyncReplayOptimizer. 2. Add `synchronize_sampling` argument to `SyncReplayOptimizer.__init__`, which is necessary for centralized critic training.
Thanks, this looks pretty good. Would it be possible to include some runnable example script so that we can run them in Jenkins, and so that users can try it out of the box? |
Oh, I added a runnable script in README in my GitHub repository:
https://github.com/wsjeon/maddpg-rllib.
Additionally, I'm creating a Singularity image now :)
Thanks.
Best,
Wonseok
…On Thu, Aug 1, 2019 at 6:34 PM Eric Liang ***@***.***> wrote:
Thanks, this looks pretty good. Would it be possible to include some
runnable example script so that we can run them in Jenkins, and so that
users can try it out of the box?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#5348?email_source=notifications&email_token=AE2DYWWNHPKQ4OWRZCGYUPTQCNQIRA5CNFSM4IIWTVH2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD3MCL2A#issuecomment-517481960>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AE2DYWUXFLJRX7FTXMETBPLQCNQIRANCNFSM4IIWTVHQ>
.
|
Test FAILed. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks! I pushed some changes to add the twostep_game test, remove the need for obs_space_dict / act_space_dict, and move it to contrib/MADDPG
.
Test FAILed. |
Test FAILed. |
Test FAILed. |
Test FAILed. |
Test FAILed. |
Test PASSed. |
What do these changes do?
I refactored OpenAI/MADDPG implementation in RLlib and checked the performance.
Related issue number
Closes #4654
Linter
scripts/format.sh
to lint the changes in this PR.