no code implementations • 20 Nov 2024 • Kevin Godin-Dubois, Karine Miras, Anna V. Kononova
Agents were trained under three different regimes (one-shot, scaffolding, interactive), and the results showed that the latter two cases outperform direct training in terms of generalization capabilities.
no code implementations • 31 Jul 2024 • Kevin Godin-Dubois, Sylvain Cussat-Blanc, Yves Duthen
To tackle the challenge of producing tractable phylogenetic trees in contexts where complete information is available, we introduce APOGeT: an online, pluggable, clustering algorithm for a stream of genomes.
no code implementations • 31 Jul 2024 • Kevin Godin-Dubois, Olivier Weissl, Karine Miras, Anna V. Kononova
We introduce here the concept of Artificial General Creatures (AGC) which encompasses "robotic or virtual agents with a wide enough range of capabilities to ensure their continued survival".