Generalising Multi-Agent Cooperation through Task-Agnostic Communication

1 code implementation • 11 Mar 2024 • Dulhan Jayalath, Steven Morad, Amanda Prorok

Our objective is to learn a fixed-size latent Markov state from a variable number of agent observations.

Multi-agent Reinforcement Learning

Does Double Descent Occur in Self-Supervised Learning?

1 code implementation • 15 Jul 2023 • Alisia Lupidi, Yonatan Gideoni, Dulhan Jayalath

Most investigations into double descent have focused on supervised models while the few works studying self-supervised settings find a surprising lack of the phenomenon.

Self-Supervised Learning

Recursive Algorithmic Reasoning

1 code implementation • 1 Jul 2023 • Jonas Jürß, Dulhan Jayalath, Petar Veličković

Learning models that execute algorithms can enable us to address a key problem in deep learning: generalizing to out-of-distribution data.