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.
Cite
@article{arxiv.1903.04698,
title = {Generation of ice states through deep reinforcement learning},
author = {Kai-Wen Zhao and Wen-Han Kao and Kai-Hsin Wu and Ying-Jer Kao},
journal= {arXiv preprint arXiv:1903.04698},
year = {2019}
}