Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion

2026-07-11

AI Summary

This work addresses the challenge of distributional shift that often causes offline-trained surrogate models for inertial confinement fusion (ICF) to fail during optimization. The authors propose Co4ICF, a novel framework that enables, for the first time, the co-evolution of physics-informed surrogate models and a Proximal Policy Optimization (PPO) reinforcement learning optimizer. In this closed-loop system, the surrogate model is continuously fine-tuned online using trajectories generated by the policy, while the optimizer treats the surrogate as a fast-query environment. This co-evolutionary mechanism effectively mitigates out-of-distribution generalization issues, achieving a posterior yield of 246.9% in an unseen 2D-MULTI setting—significantly outperforming baseline methods—and a normalized yield of 146.1% in 1D-MULTI. Ablation studies confirm that the performance gains stem directly from the co-evolution design.

Abstract

Offline-trained surrogates for Inertial Confinement Fusion (ICF) suffer a well-known failure mode that iterative optimizers drive inputs into out-of-distribution (OOD) regions where predictions become unreliable. Here we present Co4ICF, a co-evolving framework that couples a physics-informed surrogate with a PPO-based pulse optimizer. The surrogate is iteratively fine-tuned on policy-induced trajectories, correcting extrapolation errors as the optimizer shifts the input distribution; the optimizer queries this evolving surrogate as a fast environment. In the 1D MULTI environment, Co4ICF achieves 146.1% normalized yield based on current laser design baseline; as a post-hoc cross-fidelity check, the optimized pulse further attains 246.9% normalized yield when directly evaluated in 2D-MULTI without any 2D training or fine-tuning. Budget-matched ablations support that the gains are not explained solely by additional simulation data and are consistent with the co-evolving mechanism playing a key role. We release a large-scale MULTI-IFE simulation dataset to support future benchmarking.

Problem

• Inertial Confinement Fusion
• surrogate model
• out-of-distribution
• iterative optimization
• prediction reliability

Innovation

• co-evolving framework
• physics-informed surrogate
• RL-based pulse optimization
• out-of-distribution correction
• inertial confinement fusion