策略引导的蒙特卡罗：强化学习马尔可夫链动力学
Policy Guided Monte Carlo: Reinforcement Learning Markov Chain Dynamics
摘要：
我们介绍了\textit{Policy Guided Monte Carlo}（PGMC），一个计算框架，使用强化学习，以改善马尔可夫链蒙特卡罗（MCMC）采样。该方法是普遍适用的，公正的，开辟了一条新的路径，自动发现有效的MCMC采样器。在发展了一个一般的理论，我们展示了一些PGMC的前景上的伊辛模型的戈薇晶格，包括当该模型是在其计算上具有挑战性的戈薇自旋冰制度。在这里，我们表明PGMC能够自动机器学习有效的MCMC更新，而无需手头的物理先验知识。
英文摘要：
We introduce \textit{Policy Guided Monte Carlo} (PGMC), a computational framework using reinforcement learning to improve Markov chain Monte Carlo (MCMC) sampling. The methodology is generally applicable, unbiased and opens up a new path to automated discovery of efficient MCMC samplers. After developing a general theory, we demonstrate some of PGMC's prospects on an Ising model on the kagome lattice, including when the model is in its computationally challenging kagome spin ice regime. Here, we show that PGMC is able to automatically machine learn efficient MCMC updates without a priori knowledge of the physics at hand.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
