Nonlinear Photonic Neuromorphic Chips for Spiking Reinforcement Learning

TL;DR

This paper introduces a novel photonic neuromorphic chip capable of nonlinear computations and demonstrates its application in low-latency, energy-efficient spiking reinforcement learning for real-time control tasks.

Contribution

It presents the first photonic spiking reinforcement learning architecture with integrated nonlinear computations and a collaborative training-inference framework.

Findings

Achieved 1.39 TOPS/W linear computation efficiency.

Demonstrated 987.65 GOPS/W nonlinear computation efficiency.

Real-time control tasks with low latency of 320 ps.

Abstract

Photonic computing chips have made significant progress in accelerating linear computations, but nonlinear computations are usually implemented in the digital domain, which introduces additional system latency and power consumption, and hinders the implementation of fully-functional photonic neural network chips. Here, we propose and fabricate a 16-channel programmable incoherent photonic neuromorphic computing chip by co-designing a simplified MZI mesh and distributed feedback lasers with saturable absorber array using different materials, enabling implementation of both linear and nonlinear spike computations in the optical domain. Furthermore, previous studies mainly focused on supervised learning and simple image classification tasks. Here, we propose a photonic spiking reinforcement learning (RL) architecture for the first time, and develop a software-hardware collaborative training-inference framework to address the challenge of training spiking RL models. We achieve large-scale, energy-efficient (photonic linear computation: 1.39 TOPS/W, photonic nonlinear computation: 987.65 GOPS/W) and low-latency (320 ps) end-to-end deployment of an entire layer of photonic spiking RL. Two RL benchmarks include the discrete CartPole task and the continuous Pendulum tasks are demonstrated experimentally based on spiking proximal policy optimization algorithm. The hardware-software collaborative computing reward value converges to 200 (-250) for the CartPole tasks, respectively, comparable to that of a traditional PPO algorithm. This experimental demonstration addresses the challenge of the absence of large-scale photonic nonlinear spike computation and spiking RL training difficulty, and presents a high-speed and low-latency photonic spiking RL solution with promising application prospects in fields such as real-time decision-making and control for robots and autonomous driving.