Seminar on April 12, 2021

Title

Learning to Communicate in Multi-Agent Systems

Speaker

Dr. Amanda Prorok, University of Cambridge, UK

When and Where

April 12, 2021, 16:00-17:00
Online on Zoom, see TAS Resilience Node for registration or send an email to Valeria Cardellini

Abstract

Effective communication is key to successful multi-agent coordination. Yet it is far from obvious what, how and when information needs to be shared among agents that aim to solve cooperative tasks. In this talk, I discuss our recent work on using Graph Neural Networks (GNNs) to solve multi-agent coordination problems. In my first case-study, I show how we use GNNs to find a decentralized solution to the multi-agent path finding problem, which is known to be NP-hard. I demonstrate how our policy is able to achieve near-optimal performance, at a fraction of the real-time computational cost. Secondly, I show how GNN-based reinforcement learning can be leveraged to learn inter-agent communication policies. In this case-study, I demonstrate how non-shared optimization objectives can lead to adversarial communication strategies. Finally, I address the challenge of learning robust communication policies, enabling a multi-agent system to maintain high performance in the presence of anonymous non-cooperative agents that communicate faulty, misleading or manipulative information.

Speaker’s Short Bio

Amanda Prorok is a University Lecturer in the Department of Computer Science and Technology, University of Cambridge. Her research covers robotic systems and robot networks including algorithms for coordination, control and planning, with applications to multi-vehicle systems, automated transport, and robot swarms. Her work has been presented at a number of conferences, and published in the leading robotics journals, IEEE T-RO (Transactions on Robotics) and IJRR (International Journal of Robotics Research).

Before joining Cambridge, Amanda was a Postdoctoral Researcher at the University of Pennsylvania in the General Robotics, Automation, Sensing and Perception laboratory. She holds a PhD from École Polytechnique Fédérale de Lausanne in Switzerland, where her thesis was awarded the 2014 Asea Brown Boveri (ABB) award for the best thesis in Computer Science, Automatics, and Telecommunications.