Offline Contextual Bayesian Optimization for Nuclear Fusion

TL;DR

This paper introduces an offline Bayesian optimization method to learn control strategies for nuclear fusion reactors using simulations, aiming to improve reaction stability without real-world experimentation.

Contribution

The paper proposes a theoretically grounded Bayesian optimization algorithm tailored for offline learning of plasma control policies in nuclear fusion.

Findings

More efficient use of simulation resources.

Effective offline learning of control policies.

Potential for improved reactor stability.

Abstract

Nuclear fusion is regarded as the energy of the future since it presents the possibility of unlimited clean energy. One obstacle in utilizing fusion as a feasible energy source is the stability of the reaction. Ideally, one would have a controller for the reactor that makes actions in response to the current state of the plasma in order to prolong the reaction as long as possible. In this work, we make preliminary steps to learning such a controller. Since learning on a real world reactor is infeasible, we tackle this problem by attempting to learn optimal controls offline via a simulator, where the state of the plasma can be explicitly set. In particular, we introduce a theoretically grounded Bayesian optimization algorithm that recommends a state and action pair to evaluate at every iteration and show that this results in more efficient use of the simulator.