# Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach

## TL;DR

This paper explores parallelization strategies for Deep Reinforcement Learning in active flow control, demonstrating that running multiple simulations in parallel significantly accelerates training, enabling more complex fluid mechanics problems to be tackled.

## Contribution

It introduces a parallelization approach for DRL that achieves near-perfect speedups up to the batch size, facilitating faster exploration of complex flow control strategies.

## Key findings

- Perfect speedups up to batch size of the DRL agent.
- Suboptimal but still effective scaling beyond batch size.
- Enabling study of more complex fluid mechanics problems.

## Abstract

Deep Reinforcement Learning (DRL) has recently been proposed as a methodology to discover complex Active Flow Control (AFC) strategies [Rabault, J., Kuchta, M., Jensen, A., Reglade, U., & Cerardi, N. (2019): "Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control", Journal of Fluid Mechanics, 865, 281-302]. However, while promising results were obtained on a simple 2D benchmark flow at a moderate Reynolds number, considerable speedups will be required to investigate more challenging flow configurations. In the case of DRL trained with Computational Fluid Dynamics (CFD) data, it was found that the CFD part, rather than training the Artificial Neural Network, was the limiting factor for speed of execution. Therefore, speedups should be obtained through a combination of two approaches. The first one, which is well documented in the literature, is to parallelize the numerical simulation itself. The second one is to adapt the DRL algorithm for parallelization. Here, a simple strategy is to use several independent simulations running in parallel to collect experiences faster. In the present work, we discuss this solution for parallelization. We illustrate that perfect speedups can be obtained up to the batch size of the DRL agent, and slightly suboptimal scaling still takes place for an even larger number of simulations. This is, therefore, an important step towards enabling the study of more sophisticated Fluid Mechanics problems through DRL.