# Controlling chaotic itinerancy in laser dynamics for reinforcement learning

arXiv: https://arxiv.org/abs/2205.05987 · HTML: https://mlsanity.com/paper/2205.05987/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 70 references that are in the map.
- First posted on arXiv 12 May 2022.

## Builds on (most cited first, 9 of 9)

- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [Ultrafast photonic reinforcement learning based on laser chaos](https://mlsanity.com/paper/1704.04379/) (2017)
- [Designing spontaneous behavioral switching via chaotic itinerancy](https://mlsanity.com/paper/2002.08332/) (2020)
- [Efficient Decision-Making by Volume-Conserving Physical Object](https://mlsanity.com/paper/1412.6141/) (2014)
- [Scalable photonic reinforcement learning by time-division multiplexing of laser chaos](https://mlsanity.com/paper/1803.09425/) (2018)
- [DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks](https://mlsanity.com/paper/1905.02248/) (2019)
- [Dynamic channel selection in wireless communications via a multi-armed bandit algorithm using laser chaos time series](https://mlsanity.com/paper/1909.03629/) (2019)
- [Arm order recognition in multi-armed bandit problem with laser chaos time series](https://mlsanity.com/paper/2005.13085/) (2020)
- [Lotka-Volterra competition mechanism embedded in a decision-making method](https://mlsanity.com/paper/1907.12399/) (2019)

## Built on by (most cited first, 7 of 7)

- [Parallel photonic accelerator for decision making using optical spatiotemporal chaos](https://mlsanity.com/paper/2210.06976/) (2022)
- [Conflict-free joint decision by lag and zero-lag synchronization in laser network](https://mlsanity.com/paper/2307.15373/) (2023)
- [Asymmetric leader-laggard cluster synchronization for collective decision-making with laser network](https://mlsanity.com/paper/2312.02537/) (2023)
- [Parallel bandit architecture based on laser chaos for reinforcement learning](https://mlsanity.com/paper/2205.09543/) (2022)
- [Attractor-merging Crises and Intermittency in Reservoir Computing](https://mlsanity.com/paper/2504.12695/) (2025)
- [Autocorrelation effects in a stochastic-process model for solving two-armed bandit problems](https://mlsanity.com/paper/2603.05559/) (2026)
- [Massively Parallel Reinforcement Learning with a Chaotic Reconfigurable Clockless Chip](https://mlsanity.com/paper/2609.36347/) (2026)

## Abstract (arXiv)

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.