Sevenmachines

No words go here

niall

8-Minute Read

There is a natural human psychology for consolidation over exploration. Inherently we can feel that successes are something to be protected, perhaps to build on, but never to take risks with. This is a easy mindset to develop, but why is it dangerous? At first glance, there are many positive aspects, especially for close-horizon time scales. But across longer periods of time, the negatives significantly outweigh those positives. We find ourselves favouring entrenchment over mobility, and change…

niall

2-Minute Read

This is the first paper (in review) in the Multi-agent learning in dynamic systems series. Developing new algorithms to optimise task allocation in multi-agent systems. Q-learning, historical reward convolution, and dynamically adaptable risk-based system exploration approaches are developed.

Series

Categories

Recent Posts