Gym-preCICE: Reinforcement learning environments for active flow control

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 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. Gym-preCICE provides a framework for seamless non-invasive integration of RL and AFC, as well as a playground for applying RL algorithms in various AFC-related engineering applications. & COPY; 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

Automated summary

Active flow control (AFC) involves manipulating fluid flow over time to achieve a desired performance or efficiency. Reinforcement Learning (RL) can be utilized for dynamic optimization in AFC as a sequential optimization task. Gym-preCICE is introduced as a Python adapter fully compliant with Gymnasium API to facilitate designing and developing RL environments for single- and multi-physics AFC applications. Gym-preCICE uses preCICE, an open-source coupling library, for information exchange between a controller (actor) and an AFC simulation environment, providing a framework for seamless integration of RL and AFC.