No-regret Dynamics for Multi-agent Learning
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact James Allingham.
Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders.
We review multi-agent learning, including equilibrium concepts such as Nash equilibrium and correlated equilibrium, as well as online-learning-based algorithms for computing them such as no-regret dynamics. These techniques were instrumental in the recent breakthrough of human-level performance in the board game Diplomacy by a computer.
Preparatory reading: Tim Roughgarden, Twenty Lectures on Algorithmic Game Theory, Ch. 17. https://theory.stanford.edu/~tim/f13/l/l17.pdf
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|