Quantum Multi-Agent Meta Reinforcement Learning

TL;DR

This paper introduces Quantum Meta Multi-Agent Reinforcement Learning (QM2ARL), leveraging quantum neural networks' dual trainable parameters for meta-learning, regularization, and memory, demonstrating high reward and rapid adaptation in simulations.

Contribution

It proposes a novel quantum meta-reinforcement learning framework utilizing angle and pole parameters, with regularization and pole memory for improved learning and adaptation.

Findings

High reward and fast convergence in simulations

Effective pole memory for quick adaptation

Theoretical proof of convergence under regularization

Abstract

Although quantum supremacy is yet to come, there has recently been an increasing interest in identifying the potential of quantum machine learning (QML) in the looming era of practical quantum computing. Motivated by this, in this article we re-design multi-agent reinforcement learning (MARL) based on the unique characteristics of quantum neural networks (QNNs) having two separate dimensions of trainable parameters: angle parameters affecting the output qubit states, and pole parameters associated with the output measurement basis. Exploiting this dyadic trainability as meta-learning capability, we propose quantum meta MARL (QM2ARL) that first applies angle training for meta-QNN learning, followed by pole training for few-shot or local-QNN training. To avoid overfitting, we develop an angle-to-pole regularization technique injecting noise into the pole domain during angle training. Furthermore, by exploiting the pole as the memory address of each trained QNN, we introduce the concept of pole memory allowing one to save and load trained QNNs using only two-parameter pole values. We theoretically prove the convergence of angle training under the angle-to-pole regularization, and by simulation corroborate the effectiveness of QM2ARL in achieving high reward and fast convergence, as well as of the pole memory in fast adaptation to a time-varying environment.