# Photonic architecture for reinforcement learning

## TL;DR

This paper proposes a scalable photonic architecture for reinforcement learning that leverages single-photon evolution, demonstrating robustness to noise and capabilities for abstraction and generalization, advancing AI hardware development.

## Contribution

It introduces a novel photonic implementation of reinforcement learning algorithms, combining experimental feasibility with features like abstraction and generalization.

## Key findings

- Realistic noise levels can be tolerated or beneficial.
- The architecture enables abstraction and generalization.
- Implementation is feasible with near-term technology.

## Abstract

The last decade has seen an unprecedented growth in artificial intelligence and photonic technologies, both of which drive the limits of modern-day computing devices. In line with these recent developments, this work brings together the state of the art of both fields within the framework of reinforcement learning. We present the blueprint for a photonic implementation of an active learning machine incorporating contemporary algorithms such as SARSA, Q-learning, and projective simulation. We numerically investigate its performance within typical reinforcement learning environments, showing that realistic levels of experimental noise can be tolerated or even be beneficial for the learning process. Remarkably, the architecture itself enables mechanisms of abstraction and generalization, two features which are often considered key ingredients for artificial intelligence. The proposed architecture, based on single-photon evolution on a mesh of tunable beamsplitters, is simple, scalable, and a first integration in portable systems appears to be within the reach of near-term technology.