Injection Optimization at Particle Accelerators via Reinforcement Learning: From Simulation to Real-World Application

TL;DR

This paper demonstrates how reinforcement learning, specifically the Soft Actor-Critic algorithm, can be used to optimize particle accelerator injection processes, achieving human-level performance more efficiently in real-world settings.

Contribution

The paper introduces a reinforcement learning framework with domain randomization for optimizing particle accelerator injection, successfully transferring from simulation to live operation.

Findings

RL agent achieved human operator level performance

Optimization was completed significantly faster than traditional methods

The approach demonstrated robustness and generalization in live accelerator environments

Abstract

Optimizing the injection process in particle accelerators is crucial for enhancing beam quality and operational efficiency. This paper presents a framework for utilizing Reinforcement Learning (RL) to optimize the injection process at accelerator facilities. By framing the optimization challenge as an RL problem, we developed an agent capable of dynamically aligning the beam's transverse space with desired targets. Our methodology leverages the Soft Actor-Critic algorithm, enhanced with domain randomization and dense neural networks, to train the agent in simulated environments with varying dynamics promoting it to learn a generalized robust policy. The agent was evaluated in live runs at the Cooler Synchrotron COSY and it has successfully optimized the beam cross-section reaching human operator level but in notably less time. An empirical study further validated the importance of each architecture component in achieving a robust and generalized optimization strategy. The results demonstrate the potential of RL in automating and improving optimization tasks at particle acceleration facilities.