Speaker
Description
We present an MBRL-based approach for optimizing beam injection into the Alternating Gradient Synchrotron (AGS) using a fully differentiable in silico environment. Beam diagnostics from turn-by-turn beam position monitors throughout the AGS lattice are leveraged to characterize injection quality by quantifying beam survival and localizing beam losses along the ring. These observables are incorporated into an MPC reward structure, enabling the controller to directly optimize beam survival and system identification. Such an MPC planner can be used to train an MBRL agent. The simulation framework models nonlinear beam dynamics, lattice optics, and operational constraints, allowing gradients to be propagated through the environment for efficient policy learning. To ensure robustness and generalization, domain randomization is applied over initial beam distributions and lattice misalignments during RL agent training. This work establishes a foundation for robust, model-driven injection optimization and supports future translation of RL-based control strategies to accelerator operations.
| Student | No |
|---|
