University of Cambridge > Talks.cam > Accelerate Lunchtime Seminar Series > A Multi-Agent System for Mathematical Discovery

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

A Multi-Agent System for Mathematical Discovery

Download to your calendar using vCal

If you have a question about this talk, please contact Sam Nallaperuma-Herzberg .

The practice of working mathematicians shows that the process of discovering novel, interesting mathematics often involves discussions amongst multiple experts and making mistakes. Making false (yet interesting) conjectures and failed attempts to prove them can be driving forces for progress in the field. Moreover, there is an inherent social aspect to judging both the correctness and value of research level math. In this talk, I discuss our proposal for a multi-agent reinforcement learning architecture that incorporates these aspects of the mathematical process, aiming to learn interesting statements purely from mathematical data.

This talk is part of the Accelerate Lunchtime Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

FW 11, William Gates Building. Zoom link: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon Centre for Mathematical Sciences, MR 9 Biochemistry Lecture Theatre, Gurdon Institute, Tennis Court Road, Cambridge

Other talks

C2D3 Computational Biology Annual Symposium 2026 Title to be confirmed How Far Can Good Go Without God? The Limits of a Naturalistic Ethic Animating urbanism: the demotic multiplicities of seeing cities digitally Title TBC Title to be confirmed
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity