Controlling chaotic itinerancy in laser dynamics for reinforcement learning
This work addresses the need for brain-like functionalities in photonic hardware accelerators for complex machine learning tasks, though it appears incremental in applying chaotic dynamics to a specific domain.
The authors tackled the problem of solving the multi-armed bandit problem in reinforcement learning by controlling chaotic itinerancy in a multi-mode semiconductor laser, resulting in a method that outperforms conventional approaches for large-scale problems with high scalability.
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.