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

Develop new learning algorithm: PPO #239

Open
nick-harder opened this issue Nov 6, 2023 · 2 comments · May be fixed by #462
Open

Develop new learning algorithm: PPO #239

nick-harder opened this issue Nov 6, 2023 · 2 comments · May be fixed by #462
Assignees
Labels
enhancement An optional feature or enhancement feature A required feature implementation

Comments

@nick-harder
Copy link
Member

We should start working on a new DRL algorithm based on MA PPO algorithm, it promises significant speed improvements, and would solver the critique of the centralized critic approach

@nick-harder nick-harder added feature A required feature implementation enhancement An optional feature or enhancement labels Nov 6, 2023
@nick-harder
Copy link
Member Author

This tasks has been given low priority as other issues need to be adressed first

@kim-mskw kim-mskw linked a pull request Oct 28, 2024 that will close this issue
10 tasks
@kim-mskw
Copy link
Contributor

kim-mskw commented Nov 6, 2024

The general structure is ready on the PPO branch and runnable with one gradient step. However, the conversion for a single agent seems to get stuck in extreme values, so nothing too valuable is learned.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement An optional feature or enhancement feature A required feature implementation
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants