Beacon, a lightweight deep reinforcement learning benchmark library for flow control
This addresses the need for standardized benchmarks in the emerging domain of flow control using deep reinforcement learning, though it is incremental as it builds on existing algorithms and environments.
The authors tackled the lack of reproducibility and benchmarking in deep reinforcement learning for flow control by introducing Beacon, an open-source library with seven lightweight 1D and 2D flow control problems, providing reference solutions.
Recently, the increasing use of deep reinforcement learning for flow control problems has led to a new area of research, focused on the coupling and the adaptation of the existing algorithms to the control of numerical fluid dynamics environments. Although still in its infancy, the field has seen multiple successes in a short time span, and its fast development pace can certainly be partly imparted to the open-source effort that drives the expansion of the community. Yet, this emerging domain still misses a common ground to (i) ensure the reproducibility of the results, and (ii) offer a proper ad-hoc benchmarking basis. To this end, we propose Beacon, an open-source benchmark library composed of seven lightweight 1D and 2D flow control problems with various characteristics, action and observation space characteristics, and CPU requirements. In this contribution, the seven considered problems are described, and reference control solutions are provided. The sources for the following work are available at https://github.com/jviquerat/beacon.