Talk

Single-Agent Policies for …

Event: 17th European Conference on Multi-Agent Systems (EUMAS 2020), 14 September 2020 — Thessaloniki, Greece (held virtually)

Modelling and planning as well as Machine Learning techniques such as Reinforcement Learning are often difficult in multi-agent problems. With increasing numbers of agents …

Ignorance Is Bliss: Noise …

Event: Collective Dynamics Seminar, 19 October 2019

Reinforcement Learning for Multi-Agent systems is hard! Can we instead get away with just training a single agent and then deploying it on many agents? Maybe, but there are catches.

This talk explored a ’toy’ problem of multi-agent …

Bi-Level Optimisation for …

Event: TB-Phase Project, 7 August 2018

We look at the use of bi-level optimisation techniques to solve a number of standard assignment and routing problems.

Download the slides