-
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
Feat: feed forward sebulba MAPPO #1161
Conversation
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.
Just 1 change and then a though that waiting for the rec-IQL PR may be easiest
* implemented * cleaning * pipeline streamline * update * pr suggestions * cleaning * cleaning * pin gymnasium version * requirements update * cleaning
* feat: inital iql * fix: concat of trajs from diffrent actors * fix: deadlock caused by deleting when buffer is full * fix: major changes to the ratelimiter configs and a separate buffer per acotr * docs: minor comment chnage * feat: changed file structer, removed the threadlifetime and made minor chanage * chore: pre-commit * chore: minor changes * feat: Blocking rate limiter & replay ratio param * chor: small changes * feat: commen shutdown function * chor: updated for rec_ippo --------- Co-authored-by: Sasha Abramowitz <reallysasha@gmail.com>
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.
🏅
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.
everything looks sound to me!
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.
🔥 🚒 🧯 🧨 🧑🚒
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.
LGTM. Excellent work 🔥
* implemented * cleaning * cleaning * cleaning * clean pipeline * pin gymnasium version * requirements update * cleaning * Feat: sebulba recurrent ippo (#1156) * implemented * cleaning * pipeline streamline * update * pr suggestions * cleaning * cleaning * pin gymnasium version * requirements update * cleaning * Feat Sebulba recurrent IQL (#1148) * feat: inital iql * fix: concat of trajs from diffrent actors * fix: deadlock caused by deleting when buffer is full * fix: major changes to the ratelimiter configs and a separate buffer per acotr * docs: minor comment chnage * feat: changed file structer, removed the threadlifetime and made minor chanage * chore: pre-commit * chore: minor changes * feat: Blocking rate limiter & replay ratio param * chor: small changes * feat: commen shutdown function * chor: updated for rec_ippo --------- Co-authored-by: Sasha Abramowitz <reallysasha@gmail.com> * thread stopping update * cleaning * gym obs spec * obs space fix * obs dict key rename * iql fix * cleaning --------- Co-authored-by: Louay Ben nessir <91753931+Louay-Ben-nessir@users.noreply.github.com> Co-authored-by: Sasha Abramowitz <reallysasha@gmail.com>
No description provided.