collaborators

8 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.RO2026

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…

physics.comp-ph2026

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…

cs.LG2025

An entropy-optimal path to humble AI

Davide Bassetti, Lukáš Pospíšil, 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…