Online learning stabilizes plasma controls with limited data

Online Imitation Learning for Stabilizing Vlasov--Poisson Plasmas

Machine Learning

Summary

Controlling unstable plasma, which is important for nuclear fusion, is hard especially when only limited information about the plasma is available. The authors studied how machines can learn to imitate a perfect controller that sees everything but must work using only limited data. They found that simply copying behavior leads to worsening performance over time, but interactive learning that keeps updating the controller can prevent this. Their new algorithm successfully keeps the plasma stable longer in computer simulations.

What this means in practice

  • For fusion plant operators: Maintain plasma stability over longer periods using controllers that learn from partial data in real time.
  • For control systems engineers: Develop online learning controllers that adapt to partially observed states to improve stability in complex physical systems.

Authors

Xiaofan Xia, Qin Li, Wenlong Mou

Abstract

We study the problem of controlling instability in the Vlasov--Poisson plasma systems, a fundamental challenge for nuclear fusion control. Motivated by the partial observability of plasma states in practice, we investigate imitation learning algorithms that learn from a fully-observable expert controller, but operate under macroscopic measurements. We theoretically establish a separation between online and offline imitation learning --- even a small behavior cloning error leads to error compounding that exponentially amplifies instability over time. By way of contrast, the online imitation learning loss can polynomially control the stability of rollout trajectories. We then propose a DAgger-style algorithm that learns the stabilizing controller under partial observability. Simulation results on a 1D Vlasov--Poisson system demonstrate that our algorithm can effectively stabilize plasma instabilities over longer time horizons than behavior cloning.