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

arXiv:2402.16543v1 Announce Type: cross
Abstract: In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control system, provides a virtual testbed for safety-critical control applications, and allows to gain a deep understanding of the control mechanisms. While reinforcement learning has been applied successfully in a number of rather simple flow control benchmarks, a major bottleneck toward real-world applications is the …

abstract applications arxiv control cs.ce cs.lg environments flow loop optimization physics.flu-dyn reinforcement reinforcement learning safety safety-critical simulation simulations solve type virtual