AINeutralarXiv – CS AI · 5h ago6/10
🧠
Koopman-Assisted Reinforcement Learning
Researchers develop Koopman-assisted reinforcement learning algorithms that transform nonlinear control problems into linear coordinate spaces, making Hamilton-Jacobi-Bellman methods computationally tractable for complex systems. The approach demonstrates state-of-the-art performance compared to neural network-based baselines across diverse test cases from fluid dynamics to chaotic systems.