no code implementations • 29 May 2024 • Charles Westphal, Stephen Hailes, Mirco Musolesi
In this paper, we introduce Partial Information Decomposition of Features (PIDF), a new paradigm for simultaneous data interpretability and feature selection.
no code implementations • 21 Jan 2024 • Charles Westphal, Stephen Hailes, Mirco Musolesi
Identifying the most suitable variables to represent the state is a fundamental challenge in Reinforcement Learning (RL).