Decision-making and control with diffractive optical networks
This work addresses the challenge of enabling diffractive optical networks to perform interactive decision-making and control, which could benefit applications in autonomous driving, intelligent robots, and manufacturing, representing a solid step forward but not a paradigm shift.
The authors tackled the problem of implementing decision-making and control capabilities in diffractive optical networks, which previously focused only on tasks like object recognition without environmental interaction. They proposed using deep reinforcement learning with a residual architecture to achieve human-level performance, demonstrating superior results in three classic games including Tic-Tac-Toe, Super Mario Bros., and Car Racing, with an experimental demonstration for Tic-Tac-Toe.
The ultimate goal of artificial intelligence is to mimic the human brain to perform decision-making and control directly from high-dimensional sensory input. Diffractive optical networks provide a promising solution for implementing artificial intelligence with high-speed and low-power consumption. Most of the reported diffractive optical networks focus on single or multiple tasks that do not involve environmental interaction, such as object recognition and image classification. In contrast, the networks capable of performing decision-making and control have not yet been developed to our knowledge. Here, we propose using deep reinforcement learning to implement diffractive optical networks that imitate human-level decision-making and control capability. Such networks taking advantage of a residual architecture, allow for finding optimal control policies through interaction with the environment and can be readily implemented with existing optical devices. The superior performance of these networks is verified by engaging three types of classic games, Tic-Tac-Toe, Super Mario Bros., and Car Racing. Finally, we present an experimental demonstration of playing Tic-Tac-Toe by leveraging diffractive optical networks based on a spatial light modulator. Our work represents a solid step forward in advancing diffractive optical networks, which promises a fundamental shift from the target-driven control of a pre-designed state for simple recognition or classification tasks to the high-level sensory capability of artificial intelligence. It may find exciting applications in autonomous driving, intelligent robots, and intelligent manufacturing.