7 papers
Goal-Conditioned Agents that Learn Everything All at Once
Michael Matthews, Matthew Jackson, Michael Beukman +5
A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing o…
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer
Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising altern…
WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
Guillaume Levy, Cedric Colas, Pierre-Yves Oudeyer +2
Large Language Models (LLMs) possess general world knowledge but often struggle to generate precise predictions in structured, domain-specific contexts such as simulations. These l…
When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings
Jérémy Perez, Grgur KovaÄ, Corentin Léger +5
As large language models (LLMs) start interacting with each other and generating an increasing amount of text online, it becomes crucial to better understand how information is tra…
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
Cédric Colas, Pierre Fournier, Olivier Sigaud +2
In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration. They may consider a l…
Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata
Sina Khajehabdollahi, Gautier Hamon, Marko Cvjetko +3
Discovering diverse visual patterns in continuous cellular automata (CA) is challenging due to the vastness and redundancy of high-dimensional behavioral spaces. Traditional explor…