Kim, H.S. Chai, J.-S. Gad, Kh.M. Ghergherehchi, M. Ha, D.H. Lee, J.C. Namgoong, H. JACoW Publishing Geneva, Switzerland 978-3-95450-205-9 10.18429/JACoW-Cyclotrons2019-TUP030 English 227-229 TUP030 controls cyclotron resonance network cavity Contribution to a conference proceedings 2020 2020-06 https://doi.org/10.18429/JACoW-Cyclotrons2019-TUP030 http://jacow.org/cyclotrons2019/papers/tup030.pdf Accelerator Mass Spectrometry (AMS) is a powerful method for separating rare isotopes and electrostatic type tandem accelerators have been widely used. At SungKyunKwan University, we are developing a AMS that can be used in a small space with higher resolution based on cyclotron. In contrast to the cyclotron used in conventional PET or proton therapy, the cyclotron-based AMS is characterized by high turn number and low dee voltage for high resolution. It is designed to accelerate not only 14C but also 13C or 12C. The AMS cyclotron RF control model has nonlinear characteristics due to the variable beam loading effect due to the acceleration of various particles and injected sample amounts. In this work, we proposed an AMS control system based on reinforcement learning. The proposed reinforcement learning finds the target control value in response to the environment through the learning process. We have designed a reinforcement learning based controller with RF system as an environment and verified the reinforcement learning based controller designed through the modeled cavity.