Explore and Exploit with Heterotic Line Bundle Models
This addresses the challenge of efficient model building in string theory for physicists, though it is incremental as it applies existing methods to a specific domain.
The paper tackles the problem of exploring heterotic SU(5) GUT models on CICY manifolds using deep reinforcement learning, with results showing agents outperforming random exploration by up to a factor of 1700 in finding unique models and scaling well with manifold complexity.
We use deep reinforcement learning to explore a class of heterotic $SU(5)$ GUT models constructed from line bundle sums over Complete Intersection Calabi Yau (CICY) manifolds. We perform several experiments where A3C agents are trained to search for such models. These agents significantly outperform random exploration, in the most favourable settings by a factor of 1700 when it comes to finding unique models. Furthermore, we find evidence that the trained agents also outperform random walkers on new manifolds. We conclude that the agents detect hidden structures in the compactification data, which is partly of general nature. The experiments scale well with $h^{(1,1)}$, and may thus provide the key to model building on CICYs with large $h^{(1,1)}$.