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.

Sign up for GitHub

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

Jump to bottom

Generic reward encouraging smart exploration of the tree. #216

Closed
3 tasks done
louis-gautier opened this issue Apr 29, 2022 · 3 comments
Closed
3 tasks done

Generic reward encouraging smart exploration of the tree. #216

louis-gautier opened this issue Apr 29, 2022 · 3 comments

Comments

@louis-gautier
Copy link
Collaborator

louis-gautier commented Apr 29, 2022 •
edited
Loading

Test it and make it work on:

  • nqueens
  • graphcoloring
  • TSPTW
@louis-gautier
Copy link
Collaborator Author

Associated PR is #226

@3rdCore
Copy link
Collaborator

3rdCore commented May 10, 2022

I'm wondering if we should wait for the issue #227 to be solved before trying to evaluate the improvement of that new reward or even discuss the value of the different importance weights used in the reward.

What do you think of this?

@louis-gautier
Copy link
Collaborator Author

louis-gautier commented May 11, 2022 •
edited
Loading

I don't think so because it is really hard to make the agent learn in problems with objective functions with CPReward. We can stick with CPReward for problems like nqueens for example, but I think we will need this reward to evaluate the improvement of learning with the new heterogeneous pipeline.

@3rdCore 3rdCore closed this as completed May 12, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@louis-gautier @3rdCore