Multi-Agent Systems
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 …
Continuous Control, DDPG …
Never work with angles
I’m sure if W.C. Fields was alive today and interested in machine learning he might have updated his maxim of never working with children or animals to include angles.
Many off the shelf RL algorithms seem like straightforward tools to replicate state of the art results …
Evolutionary Algorithms …
This is a summary of some work published last year at the 2019 Genetic and Evolutionary Computation Conference. Where we are looking to solve routing and allocation problems and trying to find ways to balance the increase in computational demand required when increasing the number of numbers of …
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 …