Parallel photonic accelerator for decision making using optical spatiotemporal chaos
This work addresses the scalability challenge for photonic accelerators in reinforcement learning applications, representing an incremental advance in experimental demonstrations.
The authors tackled the scalability problem in photonic decision-making for multi-armed bandit problems by proposing a parallel photonic system using optical spatiotemporal chaos, achieving online solution of a 512-armed bandit problem, which is two orders of magnitude larger than previous experiments, with a scaling exponent of 0.86 indicating improved performance.
Photonic accelerators have attracted increasing attention in artificial intelligence applications. The multi-armed bandit problem is a fundamental problem of decision making using reinforcement learning. However, the scalability of photonic decision making has not yet been demonstrated in experiments, owing to technical difficulties in physical realization. We propose a parallel photonic decision-making system for solving large-scale multi-armed bandit problems using optical spatiotemporal chaos. We solve a 512-armed bandit problem online, which is much larger than previous experiments by two orders of magnitude. The scaling property for correct decision making is examined as a function of the number of slot machines, evaluated as an exponent of 0.86. This exponent is smaller than that in previous work, indicating the superiority of the proposed parallel principle. This experimental demonstration facilitates photonic decision making to solve large-scale multi-armed bandit problems for future photonic accelerators.