Multi-condition multi-objective optimization using deep reinforcement learning

DOI10.1016/j.jcp.2022.111263OpenAlexW4225370744MaRDI QIDQ2671337

Se-Jin Kim, Donghyun You, Innyoung Kim

Publication date: 3 June 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.05945

zbMATH Keywords

shape optimizationPareto frontaerodynamic shape designdeep reinforcement learningmulti-condition multi-objective optimization

Mathematics Subject Classification ID

Mathematical programming (90Cxx) Basic methods in fluid mechanics (76Mxx) Compressible fluids and gas dynamics (76Nxx)

Related Items

Non-iterative generation of an optimal mesh for a blade passage using deep reinforcement learning

Uses Software

• MOEA/D
• XFOIL
• MOPSO
• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• MOEA/D + uniform design: a new version of MOEA/D for optimization problems with many objectives
• Hypervolume-based multiobjective optimization: theoretical foundations and practical implications
• On scalarizing functions in multiobjective optimization
• Direct shape optimization through deep reinforcement learning
• Deep reinforcement learning for the control of conjugate heat transfer
• Discretization error control for constrained aerodynamic shape optimization
• Low-fidelity 2D isogeometric aeroelastic analysis and optimization method with application to a morphing airfoil
• Shape Optimization in Electromagnetic Applications
• S<scp>HAPE</scp> O<scp>PTIMIZATION IN</scp> F<scp>LUID</scp> M<scp>ECHANICS</scp>