8 papers
Maximising the Set-Piece Return: Optimising Football Corner Tactics with Graph Reinforcement Learning
Sean Groom, Michael Groom, Francisco Belo +4
Machine learning is increasingly employed for the evaluation of football tactics. However, existing approaches focus on characterising historical actions or analyst-specified count…
Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
Michael Groom, Victor-Alexandru Darvariu, Lars Kunze +2
Unlike standard expected-return Reinforcement Learning (RL), Distributional RL (DRL) models the full return distribution, making it better-suited for uncertainty-aware and risk-sen…
Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems
Xuesong Wang, Michael Groom, Rafael Oliveira +3
Recent years have seen a surge in data-driven surrogates for dynamical systems that can be orders of magnitude faster than numerical solvers. However, many machine learning-based m…
Risk-Aware Reinforcement Learning for Mobile Manipulation
Michael Groom, James Wilson, Nick Hawes +1
For robots to successfully transition from lab settings to everyday environments, they must begin to reason about the risks associated with their actions and make informed, risk-aw…
Distillation and Interpretability of Ensemble Forecasts of ENSO Phase using Entropic Learning
Michael Groom, Davide Bassetti, Illia Horenko +1
This paper introduces a distillation framework for an ensemble of entropy-optimal Sparse Probabilistic Approximation (eSPA) models, trained exclusively on satellite-era observation…
An entropy-optimal path to humble AI
Davide Bassetti, Lukáš PospÃÅ¡il, Michael Groom +2
Progress of AI has led to very successful, but by no means humble models and tools, especially regarding (i) the huge and further exploding costs and resources they demand, and (ii…