Cultural evolution in populations of Large Language Models

1 code implementation • 13 Mar 2024 • Jérémy Perez, Corentin Léger, Marcela Ovando-Tellez, Chris Foulon, Joan Dussauld, Pierre-Yves Oudeyer, Clément Moulin-Frier

We here present a framework for simulating cultural evolution in populations of LLMs, allowing the manipulation of variables known to be important in cultural evolution, such as network structure, personality, and the way social information is aggregated and transformed.

Evolving Reservoirs for Meta Reinforcement Learning

1 code implementation • 9 Dec 2023 • Corentin Léger, Gautier Hamon, Eleni Nisioti, Xavier Hinaut, Clément Moulin-Frier

At the developmental scale, we employ these evolved reservoirs to facilitate the learning of a behavioral policy through Reinforcement Learning (RL).

Meta Reinforcement Learning reinforcement-learning +1