We present a simulation strategy for the real-time dynamics of quantum fields, inspired by reinforcement learning. It builds on the complex Langevin approach, which it amends with system specific prior information, a necessary prerequisite to overcome this exceptionally severe sign problem. The optimization process underlying our machine learning approach is made possible by deploying inherently stable solvers of the complex Langevin stochastic process and a novel optimality criterion derived from insight into so-called boundary terms. This conceptual and technical progress allows us to both significantly extend the range of real-time simulations in 1+1d scalar field theory beyond the state-of-the-art and to avoid discretization artifacts that plagued previous real-time field theory simulations. Limitations of and promising future directions are discussed.
Lattice extraction of the Collins-Soper kernel using the auxiliary field representation of the Wilson line
Institute of Physics, National Yang Ming Chiao Tung University（国立阳明交通大学物理研究所）；Centre for High Energy Physics, Chung-Yuan Christian University（中原大学高能物理中心）；Physics Division, Argonne National Laboratory（阿贡国家实验室物理部）
Lattice QCD Determination of the Collins-Soper Kernel in the Continuum and Physical Mass Limits
Shanghai Jiao Tong University（上海交通大学）；Tsung-Dao Lee Institute, Shanghai Jiao Tong University（上海交大李政道研究所）；South China Normal University（华南师范大学）；University of Maryland, College Park（马里兰大学帕克分校）；Chinese Academy of Sciences（中国科学院）；Shanghai Normal University（上海师范大学）；Universität Regensburg（雷根斯堡大学）
The Collins-Soper kernel from a vacuum soft function
Institute of Physics, National Yang Ming Chiao Tung University（国立阳明交通大学物理研究所）；Centre for High Energy Physics, Chung-Yuan Christian University（中原大学高能物理中心）；Physics Division, National Centre for Theoretical Sciences（国家理论科学中心物理部）；Physics Division, Argonne National Laboratory（阿贡国家实验室物理部）
