David Mguni

Dr. David Mguni is a Lecturer in Computer Science at Queen Mary University of London, affiliated with the School of Electronic Engineering and Computer Science. His research focuses on multi-agent systems, reinforcement learning, game theory, and decision-making under uncertainty. He holds a PhD in applied mathematics from University College London and prior degrees from the University of Cambridge and the University of London. Before academia, he was a Principal Scientist at Huawei, leading the Multi-Agent Systems team in London. His work bridges theoretical foundations with practical applications, particularly in strategic decision-making and autonomous systems. He teaches the ECS656U/ECS796P Distributed Systems course and supervises students in reinforcement learning, game theory, and optimization.

Research interests include non-zero-sum game frameworks, safe reinforcement learning (e.g., SAUTE RL), and reward shaping techniques. His publications span venues like AAMAS, NeurIPS, and IJCAI, addressing challenges in multi-agent coordination, adversarial environments, and algorithmic efficiency. Collaborations involve designing scalable methods for large systems and integrating language models into decision-making processes.

David is part of Queen Mary’s Centre for Multimodal AI, contributing to projects on socially-attentive policies, risk-aware systems, and distributed optimization. His recent work emphasizes safety in multi-agent learning (e.g., SAUTE RL), variance reduction in estimator models, and frameworks for managing adversarial scenarios. He actively seeks PhD candidates to explore reinforcement learning and game-theoretic applications.