# Photonic architecture for reinforcement learning

arXiv: https://arxiv.org/abs/1907.07503 · HTML: https://mlsanity.com/paper/1907.07503/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [A Survey on Quantum Reinforcement Learning](https://mlsanity.com/paper/2211.03464/) (2022)
- [Uncovering Instabilities in Variational-Quantum Deep Q-Networks](https://mlsanity.com/paper/2202.05195/) (2022)
- [Towards interpretable quantum machine learning via single-photon quantum walks](https://mlsanity.com/paper/2301.13669/) (2023)
- [Photonic Quantum Policy Learning in OpenAI Gym](https://mlsanity.com/paper/2108.12926/) (2021)
- [Conflict-free joint decision by lag and zero-lag synchronization in laser network](https://mlsanity.com/paper/2307.15373/) (2023)
- [Parallel bandit architecture based on laser chaos for reinforcement learning](https://mlsanity.com/paper/2205.09543/) (2022)
- [Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation](https://mlsanity.com/paper/2212.09926/) (2022)
- [Asymmetric quantum decision-making](https://mlsanity.com/paper/2305.02117/) (2023)

## Abstract (arXiv)

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.