Reinforcement Operator Learning (ROL): A hybrid DeepONet-guided reinforcement learning framework for stabilizing the Kuramoto–Sivashinsky equation
Fig 5
Mean energy with ± SEM: DeepONet RL achieves 0.397 (99.1% reduction from LQR, 64.6% from Pure TD3), with minimal SEM overlap in final steps, outperforming both baselines.