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

Fix PettingZooParallelWrapper to return fresh actions on each call to int_to_cyborg_action #5

Open
wants to merge 29 commits into
base: main
Choose a base branch
from

Conversation

hkscy
Copy link

@hkscy hkscy commented Jun 11, 2023

fixes #4 by returning actions at each step rather than a dict with potentially stale parameters every episode.

cage-challenge and others added 29 commits September 23, 2022 11:38
* Update README.md

Added basic imports for creating the environment section
Added wrappers to imports

* Fix setup path

Co-authored-by: Chris Hicks <[email protected]>
* Update requirements to include Ray@latest version (2.0.0)

* Made Ray requirements optional and separate to main requirements.

Co-authored-by: Chris Hicks <[email protected]>
Model of bandwidth usage changed to now randomly sample actions to use bandwidth and dropping actions after the bandwidth usage is exceeded
Parallel Step function now also returns data for agents that took an action as well as active agents in the environment
The balance of the DroneSwarm Scenario has been changed to weaken the effectiveness of the RetakeControl action and increase the effectiveness of the RemoveOtherSessions action
Fixing error with PettingZooParallelWrapper.py assigning malicious activity to the wrong host
Make sure list is not empty (fixes #29)
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.

PettingZooParallelWrapper generates invalid actions
4 participants