Multi-objective Bayesian optimisation for design of Pareto-optimal current drive profiles in STEP

N/A

SUBMITTED TO IEEE TRANSACTIONS ON PLASMA SCIENCE, OCTOBER 2023 [PREPRINT] 1 Multi-objective Bayesian optimisation for design of Pareto-optimal current drive profiles in STEP Theodore Brown, Stephen Marsden, Vignesh Gopakumar, Alexander Terenin, Hong Ge, and Francis Casson arXiv:2310.02669v3 [physics.plasm-ph] 3 May 2024…

related reading

• EPFL_TH5203.pdfweb.archive.org
• [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
• char23a.pdfproceedings.mlr.press
• [2606.04033] Inverse Critical Experiment Design via Gradient Optimization and a Multigroup Attention-Based Neural Network Architecturearxiv.org
• people.csail.mit.edu/jsolomon/assets/design_tradeoff.pdf?utm_source=chatgpt.compeople.csail.mit.edu
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• [2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiv.org
• Learning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV | Nature Communicationsnature.com
• Accelerating fusion science through learned plasma control — Google DeepMinddeepmind.com
• [1705.09236] Asynchronous Parallel Bayesian Optimisation via Thompson Samplingarxiv.org
• Science Needs AI Data Stocktakesaipolicyperspectives.com
• [2601.08393] Controlled LLM Training on Spectral Spherearxiv.org