Skip to content
This repository was archived by the owner on Jun 2, 2025. It is now read-only.

[Meltingpot] Fine tuning PPO #78

Draft
wants to merge 8 commits into
base: main
Choose a base branch
from
Draft

[Meltingpot] Fine tuning PPO #78

wants to merge 8 commits into from

Conversation

matteobettini
Copy link
Contributor

@matteobettini matteobettini commented Apr 24, 2024

To execute just run meltingpot_run.py

cc @ezhang7423

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 24, 2024
@ezhang7423
Copy link
Contributor

I think this can probably be merged?

@matteobettini
Copy link
Contributor Author

To be merged we would need pytorch/rl#2115

Also i would like to fine tune off-policy algos as well

@dziugasu
Copy link

dziugasu commented May 1, 2024

Hi @matteobettini, I'm a student doing a small research on MARL, specifically focused on meltingpot lib, though I'm kinda new to RL. Just wanted to ask if this config was tested, maybe there is a report for it?

@matteobettini
Copy link
Contributor Author

Hi @matteobettini, I'm a student doing a small research on MARL, specifically focused on meltingpot lib, though I'm kinda new to RL. Just wanted to ask if this config was tested, maybe there is a report for it?

Hey, we are still working on this, but it could be a good starting point if you want to use IPPO in Meltingpot

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants