Gym-preCICE: Reinforcement Learning Environments for Active Flow Control

Mosayeb Shams, Ahmed H. Elsheikh
5/3/2023
cs.LG

No official code found. Best implementation: gymprecice/gymprecice (32 stars, MIT, last commit 2024-02-14).

Abstract

Active flow control (AFC) involves manipulating fluid flow over time to achieve a desired performance or efficiency. AFC, as a sequential optimisation task, can benefit from utilising Reinforcement Learning (RL) for dynamic optimisation. In this work, we introduce Gym-preCICE, a Python adapter fully compliant with Gymnasium (formerly known as OpenAI Gym) API to facilitate designing and developing RL environments for single- and multi-physics AFC applications. In an actor-environment setting, Gym-preCICE takes advantage of preCICE, an open-source coupling library for partitioned multi-physics simulations, to handle information exchange between a controller (actor) and an AFC simulation environment. The developed framework results in a seamless non-invasive integration of realistic physics-based simulation toolboxes with RL algorithms. Gym-preCICE provides a framework for designing RL environments to model AFC tasks, as well as a playground for applying RL algorithms in various AFC-related engineering applications.

View on arXivView PDF

Code Implementations(1)

gymprecice/gympreciceCommunity71%
MIT

A framework to design and develop reinforcement learning environments for single- and multi-physics active flow control.

327PythonJul 3, 20222 years agoMIT
active-flow-controlgymnasiummulti-physicsopenai-gymprecice+3 more

Similar Papers

Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control

87% match1 repo532026

Model-based deep reinforcement learning for accelerated learning from flow simulations

83% match2024

Gym-TORAX: Open-source software for integrating RL with plasma control simulators

83% match1 repo232025

HydroGym: A Reinforcement Learning Platform for Fluid Dynamics

83% match2025

Towards Active Flow Control Strategies Through Deep Reinforcement Learning

82% match2024

Gymnasium: A Standard Interface for Reinforcement Learning Environments

82% match1 repo12.7k2024

Cite this paper

@article{shams2023gymprecice,
  title  = {Gym-preCICE: Reinforcement Learning Environments for Active Flow Control},
  author = {Mosayeb Shams and Ahmed H. Elsheikh},
  year   = {2023},
  eprint = {2305.02033},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.02033v1}
}

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/2305.02033.svg)](https://codeofpaper.com/paper/2305.02033)

Discussion