Autonomous Control of a Particle Accelerator using Deep Reinforcement Learning
This work aims to reduce tuning time for particle accelerator facilities, potentially enabling near-autonomous control, though it is incremental as it focuses on a small section.
The paper tackled the problem of controlling a particle accelerator by using deep reinforcement learning with a physics simulator, achieving better-than-human performance in particle beam current and distribution for a small section.
We describe an approach to learning optimal control policies for a large, linear particle accelerator using deep reinforcement learning coupled with a high-fidelity physics engine. The framework consists of an AI controller that uses deep neural nets for state and action-space representation and learns optimal policies using reward signals that are provided by the physics simulator. For this work, we only focus on controlling a small section of the entire accelerator. Nevertheless, initial results indicate that we can achieve better-than-human level performance in terms of particle beam current and distribution. The ultimate goal of this line of work is to substantially reduce the tuning time for such facilities by orders of magnitude, and achieve near-autonomous control.