# Offline Contextual Bayesian Optimization for Nuclear Fusion

arXiv: https://arxiv.org/abs/2001.01793 · HTML: https://mlsanity.com/paper/2001.01793/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2020.

## Built on by (most cited first, 7 of 7)

- [ExPT: Synthetic Pretraining for Few-Shot Experimental Design](https://mlsanity.com/paper/2310.19961/) (2023)
- [CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design](https://mlsanity.com/paper/2302.14015/) (2023)
- [Universality of parametric Coupling Flows over parametric diffeomorphisms](https://mlsanity.com/paper/2202.02906/) (2022)
- [On the development of a practical Bayesian optimisation algorithm for expensive experiments and simulations with changing environmental conditions](https://mlsanity.com/paper/2402.03006/) (2024)
- [Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study](https://mlsanity.com/paper/2503.08301/) (2025)
- [Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications](https://mlsanity.com/paper/2605.00068/) (2026)
- [Bayesian Optimization with Rich Auxiliary Information via LLMs](https://mlsanity.com/paper/2609.19437/) (2026)

## Abstract (arXiv)

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.