Inverse design of the transmission matrix in a random system using Reinforcement Learning
This addresses the problem of designing complex scattering systems for applications in optics or photonics, though it appears incremental as it applies reinforcement learning to a known bottleneck.
The paper tackled the inverse design of scattering systems by modifying the transmission matrix using reinforcement learning, achieving specific transmission matrices such as fixed-ratio power conversion, exceptional points, and uniform channel participation.
This work presents an approach to the inverse design of scattering systems by modifying the transmission matrix using reinforcement learning. We utilize Proximal Policy Optimization to navigate the highly non-convex landscape of the object function to achieve three types of transmission matrices: (1) Fixed-ratio power conversion and zero-transmission mode in rank-1 matrices, (2) exceptional points with degenerate eigenvalues and unidirectional mode conversion, and (3) uniform channel participation is enforced when transmission eigenvalues are degenerate.