论文标题
探索和利用异性线捆绑模型
Explore and Exploit with Heterotic Line Bundle Models
论文作者
论文摘要
我们使用深度强化学习来探索一类杂种$ su（5）$肠模型，该模型是在完整的交点Calabi Yau（Cicy）歧管上建立的。我们执行几个实验，其中训练A3C代理以搜索此类模型。在找到独特的模型时，这些代理在最有利的设置中的表现大大优于随机探索。此外，我们发现证据表明，受过训练的代理商在新歧管上也超过了随机步行者。我们得出的结论是，代理检测到紧凑数据中的隐藏结构，这部分是一般性质的。实验用$ h^{（1,1）} $很好地扩展，因此可以为用大$ h^{（1,1）} $在CICY上构建模型构建钥匙。
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 $h^{(1,1)}$.
