Taking gradients through experiments: LSTMs and memory proximal policy\n optimization for black-box quantum control

In this work we introduce the application of black-box quantum control as an\ninteresting rein- forcement learning problem to the machine learning community.\nWe analyze the structure of the reinforcement learning problems arising in\nquantum physics and argue that agents parameterized by long short-term memory\n(LSTM) networks trained via stochastic policy gradients yield a general method\nto solving them. In this context we introduce a variant of the proximal policy\noptimization (PPO) algorithm called the memory proximal policy optimization\n(MPPO) which is based on this analysis. We then show how it can be applied to\nspecific learning tasks and present results of nu- merical experiments showing\nthat our method achieves state-of-the-art results for several learning tasks in\nquantum control with discrete and continouous control parameters.\n