Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learning

Jinsu Kim, Jaemin Seo
9/12/2024
physics.plasm-phcs.AIcs.LG

No official code found. Best implementation: ZINZINBIN/RL-based-Reactor-Design-Optimization (8 stars, last commit 2026-03-20).

Abstract

This research explores the application of Deep Reinforcement Learning (DRL) to optimize the design of a nuclear fusion reactor. DRL can efficiently address the challenging issues attributed to multiple physics and engineering constraints for steady-state operation. The fusion reactor design computation and the optimization code applicable to parallelization with DRL are developed. The proposed framework enables finding the optimal reactor design that satisfies the operational requirements while reducing building costs. Multi-objective design optimization for a fusion reactor is now simplified by DRL, indicating the high potential of the proposed framework for advancing the efficient and sustainable design of future reactors.

View on arXivView PDF

Code Implementations(1)

ZINZINBIN/RL-based-Reactor-Design-OptimizationCommunity100%

Source code for nuclear fusion reactor design optimization using reinforcement learning

81Python, Jupyter NotebookJun 1, 20237 months ago
computational-physicsdesign-optimizationnuclear-reactoroptimizationplasma-physics+1 more

Similar Papers

Reactor Optimization Benchmark by Reinforcement Learning

87% match1 repo52024

Assessment of Reinforcement Learning Algorithms for Nuclear Power Plant Fuel Optimization

86% match2023

Surpassing legacy approaches to PWR core reload optimization with single-objective Reinforcement learning

84% match2024

Multistep Criticality Search and Power Shaping in Microreactors with Reinforcement Learning

83% match2024

ReactorFold: Generative discovery of nuclear reactor cores via emergent physical reasoning

81% match2025

Nuclear Microreactor Control with Deep Reinforcement Learning

79% match2025

Cite this paper

@article{kim2024design,
  title  = {Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learning},
  author = {Jinsu Kim and Jaemin Seo},
  year   = {2024},
  eprint = {2409.08231},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.08231v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.08231.svg)](https://codeofpaper.com/paper/2409.08231)

Discussion