Abstract: In this talk, I discuss our work on using Graph Neural Networks (GNNs) to solve multi-agent coordination problems. I begin by describing how we use GNNs to find a decentralized solution by learning what the agents need to communicate to one another. This communication-based policy is able to achieve near-optimal performance; moreover, when combined with an attention mechanism, we can drastically improve generalization to very-large-scale systems. Next, I consider the inverse problem: instead of optimizing agent policies, what if we could modify the navigation environment, instead? Towards that end, I introduce an environment optimization approach that guarantees the existence of complete solutions, improving agent navigation success rates over heuristic methods. Finally, I discuss challenges in the transfer of learned policies to the real world.
Bio: Amanda Prorok is Professor of Collective Intelligence and Robotics in the Department of Computer Science and Technology at Cambridge University, and a Fellow of Pembroke College. She has been honoured by numerous research awards, including an ERC Starting Grant, an Amazon Research Award, the EPSRC New Investigator Award, the Isaac Newton Trust Early Career Award, and several Best Paper awards.
Her PhD thesis was awarded the Asea Brown Boveri (ABB) prize for the best thesis at EPFL in Computer Science. She serves as Associate Editor for IEEE Robotics and Automation Letters (R-AL) and Associate Editor for Autonomous Robots (AURO).
Prior to joining Cambridge, Amanda was a postdoctoral researcher at the General Robotics, Automation, Sensing and Perception (GRASP) Laboratory at the University of Pennsylvania, USA, where she worked with Prof. Vijay Kumar. She completed her PhD at EPFL, Switzerland, with Prof. Alcherio Martinoli.
Location: We will meet only virtually. Please use the following zoom meeting information to join us:
Join Zoom Meeting
Meeting ID: 846 7722 4909
Looking forward to seeing you on Friday!