F. Carta

A. Gauntlett

F. Griffin

Y. He

We show reinforcement learning can be used to check whether a certain class of quantum field theory has a finite spectrum of stable particles.

Reinforcement learning is used to compute particle spectra in 4D N=2 supersymmetric quantum field theories by analysing quivers—finite graphs that encode the matter content of the theories. The method outperforms brute-force scans, accurately reproducing the chamber structures that divide quiver space in well-studied cases. A general algorithm for discovering such chambers in this class of theories is also presented.

We apply reinforcement learning (RL) to establish whether at a given position in the Coulomb branch of the moduli space of a 4d =2 quantum field theory (QFT) the BPS spectrum is finite. If it is, we furthermore determine the full BPS spectrum at such point in moduli space. We demonstrate that using a RL model one can efficiently determine the suitable sequence of quiver mutations of the BPS quiver that will generate the full BPS spectrum. We analyse the performance of the RL model on random BPS quivers and show that it converges to a solution various orders of magnitude faster than a systematic brute-force scan. As a result, we show that our algorithm can be used to identify all minimal chambers of a given =2 QFT, a task previously intractable with computer scanning. As an example, we recover all minimal chambers of the SU(2) Nf=4 gauge theory, and discover new minimal chambers for theories that can be realized by IIB geometric engineering.

BPS spectroscopy with reinforcement learning