Direct shape optimization through deep reinforcement learning

TL;DR

This paper demonstrates that deep reinforcement learning can be effectively applied to direct shape optimization, enabling autonomous generation of optimal shapes in fluid mechanics and beyond, with minimal prior knowledge.

Contribution

It is the first to apply DRL to shape optimization, showing that neural networks can learn to generate optimal shapes based solely on reward signals.

Findings

DRL can generate optimal aerodynamic shapes autonomously.

The method is domain-agnostic and adaptable to various shape optimization problems.

Neural networks trained with DRL can operate without prior knowledge of the shapes.

Abstract

Deep Reinforcement Learning (DRL) has recently spread into a range of domains within physics and engineering, with multiple remarkable achievements. Still, much remains to be explored before the capabilities of these methods are well understood. In this paper, we present the first application of DRL to direct shape optimization. We show that, given adequate reward, an artificial neural network trained through DRL is able to generate optimal shapes on its own, without any prior knowledge and in a constrained time. While we choose here to apply this methodology to aerodynamics, the optimization process itself is agnostic to details of the use case, and thus our work paves the way to new generic shape optimization strategies both in fluid mechanics, and more generally in any domain where a relevant reward function can be defined.