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

eligibility trace actors #74

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

Freddie-Barrell
Copy link

For my university dissertation I have created CyberBattleSim agents that make use of the reinforcement learning mechanism eligibility traces, to investigate their uses in CyberBattleSim. The results were not positive but I have pulled my agents anyway in the hope my work can be of some future help to you.

@ghost
Copy link

ghost commented Aug 17, 2022

CLA assistant check
All CLA requirements met.

@blumu
Copy link
Contributor

blumu commented Sep 9, 2022

@Freddie-Barrell Thank you for the contribution. Could you rebase your branch on the latest main? Flake8 has recently been updated and there are some minor styling issues caught in CI. You should be able to address those by linting the source files with Flake8. Thank you again!

@blumu
Copy link
Contributor

blumu commented Sep 9, 2022

@Freddie-Barrell I've just fixed a regression #79 in the reward calculation that got introduced in commit 2f6a045. The regression was preventing DQL from learning good actions. It's possible that it was also affecting your own eligibility trace actor agent. You may want to give a try on the latest main branch. Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants