Transfer learning strategies for accelerating reinforcement-learning-based flow control
This addresses the computational efficiency challenge in reinforcement-learning-based flow control for fluid dynamics applications, representing a domain-specific incremental advance.
This work tackles the problem of accelerating deep reinforcement learning for flow control by investigating transfer learning strategies, finding that progressive neural networks enable stable and efficient knowledge transfer with consistent performance gains, while fine-tuning is sensitive to pretraining duration and prone to forgetting.
This work investigates transfer learning strategies to accelerate deep reinforcement learning (DRL) for multifidelity control of chaotic fluid flows. Progressive neural networks (PNNs), a modular architecture designed to preserve and reuse knowledge across tasks, are employed for the first time in the context of DRL-based flow control. In addition, a comprehensive benchmarking of conventional fine-tuning strategies is conducted, evaluating their performance, convergence behavior, and ability to retain transferred knowledge. The Kuramoto-Sivashinsky (KS) system is employed as a benchmark to examine how knowledge encoded in control policies, trained in low-fidelity environments, can be effectively transferred to high-fidelity settings. Systematic evaluations show that while fine-tuning can accelerate convergence, it is highly sensitive to pretraining duration and prone to catastrophic forgetting. In contrast, PNNs enable stable and efficient transfer by preserving prior knowledge and providing consistent performance gains, and are notably robust to overfitting during the pretraining phase. Layer-wise sensitivity analysis further reveals how PNNs dynamically reuse intermediate representations from the source policy while progressively adapting deeper layers to the target task. Moreover, PNNs remain effective even when the source and target environments differ substantially, such as in cases with mismatched physical regimes or control objectives, where fine-tuning strategies often result in suboptimal adaptation or complete failure of knowledge transfer. The results highlight the potential of novel transfer learning frameworks for robust, scalable, and computationally efficient flow control that can potentially be applied to more complex flow configurations.