Controlling chaotic itinerancy in laser dynamics for reinforcement learning

TL;DR

This paper demonstrates how controlling chaotic itinerancy in a semiconductor laser can be used to solve reinforcement learning problems efficiently, leveraging ultrafast optical dynamics for scalable exploration.

Contribution

It introduces a novel method to control chaotic itinerancy in laser dynamics for reinforcement learning, enabling high-speed, scalable solutions to complex bandit problems.

Findings

Outperforms conventional algorithms in large-scale bandit tasks

Utilizes ultrafast optical chaotic dynamics for exploration

Provides a new approach for photonic AI hardware acceleration

Abstract

Photonic artificial intelligence has attracted considerable interest in accelerating machine learning; however, the unique optical properties have not been fully utilized for achieving higher-order functionalities. Chaotic itinerancy, with its spontaneous transient dynamics among multiple quasi-attractors, can be employed to realize brain-like functionalities. In this paper, we propose a method for controlling the chaotic itinerancy in a multi-mode semiconductor laser to solve a machine learning task, known as the multi-armed bandit problem, which is fundamental to reinforcement learning. The proposed method utilizes ultrafast chaotic itinerant motion in mode competition dynamics controlled via optical injection. We found that the exploration mechanism is completely different from a conventional searching algorithm and is highly scalable, outperforming the conventional approaches for large-scale bandit problems. This study paves the way to utilize chaotic itinerancy for effectively solving complex machine learning tasks as photonic hardware accelerators.