# Quantum Multi-Agent Meta Reinforcement Learning

arXiv: https://arxiv.org/abs/2208.11510 · HTML: https://mlsanity.com/paper/2208.11510/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 16 of 16)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Supervised learning with quantum enhanced feature spaces](https://mlsanity.com/paper/1804.11326/) (2018)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Multiagent Cooperation and Competition with Deep Reinforcement Learning](https://mlsanity.com/paper/1511.08779/) (2015)
- [Understanding the Role of Training Regimes in Continual Learning](https://mlsanity.com/paper/2006.06958/) (2020)
- [Variational Quantum Circuits for Deep Reinforcement Learning](https://mlsanity.com/paper/1907.00397/) (2019)
- [Towards Robust Evaluations of Continual Learning](https://mlsanity.com/paper/1805.09733/) (2018)
- [Reinforcement Learning with Quantum Variational Circuits](https://mlsanity.com/paper/2008.07524/) (2020)
- [Continuous-variable quantum neural networks](https://mlsanity.com/paper/1806.06871/) (2018)
- [Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms](https://mlsanity.com/paper/1901.05374/) (2019)
- [Quantum Multi-Agent Reinforcement Learning via Variational Quantum Circuit Design](https://mlsanity.com/paper/2203.10443/) (2022)
- [Optimizing quantum heuristics with meta-learning](https://mlsanity.com/paper/1908.03185/) (2019)
- [Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2](https://mlsanity.com/paper/2208.05056/) (2022)

## Built on by (most cited first, 23 of 23)

- [A Survey on Quantum Reinforcement Learning](https://mlsanity.com/paper/2211.03464/) (2022)
- [Asynchronous training of quantum reinforcement learning](https://mlsanity.com/paper/2301.05096/) (2023)
- [Toward Large-Scale Distributed Quantum Long Short-Term Memory with Modular Quantum Computers](https://mlsanity.com/paper/2503.14088/) (2025)
- [Quantum Machine Learning Architecture Search via Deep Reinforcement Learning](https://mlsanity.com/paper/2407.20147/) (2024)
- [Quantum Gradient Class Activation Map for Model Interpretability](https://mlsanity.com/paper/2408.05899/) (2024)
- [eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels](https://mlsanity.com/paper/2405.17486/) (2024)
- [Differentiable Quantum Architecture Search in Quantum-Enhanced Neural Network Parameter Generation](https://mlsanity.com/paper/2505.09653/) (2025)
- [Learning to Program Quantum Measurements for Machine Learning](https://mlsanity.com/paper/2505.13525/) (2025)
- [Scalable Quantum Convolutional Neural Networks](https://mlsanity.com/paper/2209.12372/) (2022)
- [Quantum Multi-Agent Actor-Critic Networks for Cooperative Mobile Access in Multi-UAV Systems](https://mlsanity.com/paper/2302.04445/) (2023)
- [Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization](https://mlsanity.com/paper/2311.05546/) (2023)
- [3D Scalable Quantum Convolutional Neural Networks for Point Cloud Data Processing in Classification Applications](https://mlsanity.com/paper/2210.09728/) (2022)
- [Projection Valued Measure-based Quantum Machine Learning for Multi-Class Classification](https://mlsanity.com/paper/2210.16731/) (2022)
- [Quantum Split Neural Network Learning using Cross-Channel Pooling](https://mlsanity.com/paper/2211.06524/) (2022)
- [Quantum Federated Learning with Entanglement Controlled Circuits and Superposition Coding](https://mlsanity.com/paper/2212.01732/) (2022)
- [Quantum deep Q learning with distributed prioritized experience replay](https://mlsanity.com/paper/2304.09648/) (2023)
- [Breaking Through Barren Plateaus: Reinforcement Learning Initializations for Deep Variational Quantum Circuits](https://mlsanity.com/paper/2508.18514/) (2025)
- [Two Tales of Platoon Intelligence for Autonomous Mobility Control: Enabling Deep Learning Recipes](https://mlsanity.com/paper/2307.09711/) (2023)
- [Position: Emergent Machina Sapiens Urge Rethinking Multi-Agent Paradigms](https://mlsanity.com/paper/2502.04388/) (2025)
- [Quantum-Evolutionary Neural Networks for Multi-Agent Federated Learning](https://mlsanity.com/paper/2505.15836/) (2025)
- [Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation](https://mlsanity.com/paper/2506.16718/) (2025)
- [Towards Explainable Quantum AI: Informing the Encoder Selection of Quantum Neural Networks via Visualization](https://mlsanity.com/paper/2512.14181/) (2025)
- [Quantum Advantage in Multi Agent Reinforcement Learning](https://mlsanity.com/paper/2605.14235/) (2026)

## Abstract (arXiv)

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.