Lecture image placeholder

Premium content

Access to this content requires a subscription. You must be a premium user to view this content.

Need help?
Contact us
Lecture placeholder background
VIDEO DOI: https://doi.org/10.48448/e7g0-na38

technical paper

NAML 2021

March 23, 2021

Live on Underline

Cooperative Multi-Agent Reinforcement Learning for Cyber Defense

Speakers

Please log in to leave a comment

Ahmad Ridley

almost 4 years ago

Great talk! Would adding a "restart node" action to MARL agents be an example of reconnecting shutdown nodes mentioned on future work slide? Would this action potentially improve MARL agents performance (e.g., improve avg. score)? Great job explaining differences between single-agent and multi-agent approaches.

0