Zhao, Kai WenKai WenZhaoKao, Wen HanWen HanKaoWu, Kai HsinKai HsinWuYING-JER KAO2019-07-302019-07-302019-06-0524700045https://scholars.lib.ntu.edu.tw/handle/123456789/41560510 pages, 13 figures, 2 tables. Published version© 2019 American Physical Society. We present a deep reinforcement learning framework where a machine agent is trained to search for a policy to generate a ground state for the square ice model by exploring the physical environment. After training, the agent is capable of proposing a sequence of local moves to achieve the goal. Analysis of the trained policy and the state value function indicates that the ice rule and loop-closing condition are learned without prior knowledge. We test the trained policy as a sampler in the Markov chain Monte Carlo and benchmark against the baseline loop algorithm. This framework can be generalized to other models with topological constraints where generation of constraint-preserving states is difficult.Physics - Disordered Systems and Neural Networks; Physics - Disordered Systems and Neural Networks; Physics - Statistical Mechanics10.1103/PhysRevE.99.0621062-s2.0-85067351999https://api.elsevier.com/content/abstract/scopus_id/85067351999