Symbolic Turbulence Modelling with Multi- Agent Reinforcement Learning

Master Thesis (2025)
Author(s)

Z.S. Tan Zing Shawn (TU Delft - Aerospace Engineering)

Contributor(s)

R.P. Dwight – Mentor (TU Delft - Aerodynamics)

A. Eidi – Mentor (TU Delft - Aerodynamics)

Faculty
Aerospace Engineering
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
18-11-2025
Awarding Institution
Delft University of Technology
Programme
['Aerospace Engineering']
Faculty
Aerospace Engineering
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Turbulence modelling remains a major challenge in computational fluid dynamics (CFD), as Reynolds-Averaged Navier-Stokes (RANS) closures rely on empirical relations introducing significant model-form uncertainty. Symbolic regression offers a path toward interpretable data-driven closures, but conventional Deep Symbolic Regression (DSR) struggles to efficiently explore the vast space of physically consistent expressions.

We propose a Multi-Agent Deep Symbolic Regression (MADSR) framework that reformulates turbulence model discovery as a cooperative multi-agent reinforcement learning (MARL) problem. Each agent discovers one scalar coefficient function in the tensor-basis expansion of the Reynolds-stress anisotropy tensor, sharing a common reward derived from frozen RANS evaluations. This cooperative setup promotes coordinated learning among model components.

In MADSR, the effectiveness of 2 MARL techniques, proximal policy optimization (PPO) and centralised training decentralised execution (CTDE), is investigated on symbolic turbulence modelling. Several MADSR variants are developed and tested, including a vanilla multi-agent DSR, a proximal policy optimization (PPO) based MADSR, an actor-critic MADSR, and a MAPPO-DSR inspired by multi-agent proximal policy optimization (PPODSR).

Applied to the Explicit Algebraic Reynolds-Stress Model (EARSM) and k-corrective RANS formulations, MADSR outperforms single-agent DSR in frozen RANS evaluations of the periodic-hill benchmark. The multi-agent structure enhances exploration efficiency and enables discovery of more consistent and interpretable turbulence closures. MADSR thus represents a promising step toward fully end-to-end, reinforcement-learning-based symbolic turbulence modelling.

Files

MADSR_thesis_final.pdf
(pdf | 12.7 Mb)
License info not available