Multi-Agent Equilibria: From Verification to Modification and Beyond
-
This is a past event
The classical notion of correctness in formal verification is not appropriate for multi-agent systems–-it does not capture the strategic behaviour of rational agents. As such, a different notion of correctness was proposed through the concept of rational verification. In doing so, we transform multi-agent systems into multi-player games and use game-theoretic techniques to analyse the games. In this talk, we will examine several types of games with various goals and settings, and provide algorithmic techniques to solve the problems related to rational verification. We also propose a method to modify the games should we find them "incorrect". Finally, we will look at possible avenues beyond the current work.
- Speaker
- Muhammad Najib
- Venue
- Meston G05 and Microsoft Teams