General Purpose Artificial Intelligence Systems (GPAIS): Properties, definition, taxonomy, societal implications and responsible governance

I Triguero, D Molina, J Poyatos, J Del Ser, F Herrera - Information Fusion, 2024‏ - Elsevier
Abstract Most applications of Artificial Intelligence (AI) are designed for a confined and
specific task. However, there are many scenarios that call for a more general AI, capable of …

Differentiable quality diversity

M Fontaine, S Nikolaidis - Advances in Neural Information …, 2021‏ - proceedings.neurips.cc
Quality diversity (QD) is a growing branch of stochastic optimization research that studies the
problem of generating an archive of solutions that maximize a given objective function but …

pyribs: A bare-bones python library for quality diversity optimization

B Tjanaka, MC Fontaine, DH Lee, Y Zhang… - Proceedings of the …, 2023‏ - dl.acm.org
Recent years have seen a rise in the popularity of quality diversity (QD) optimization, a
branch of optimization that seeks to find a collection of diverse, high-performing solutions to …

Goals as reward-producing programs

G Davidson, G Todd, J Togelius, TM Gureckis… - Nature Machine …, 2025‏ - nature.com
People are remarkably capable of generating their own goals, beginning with child's play
and continuing into adulthood. Despite considerable empirical and computational work on …

Evolutionary algorithms for parameter optimization—thirty years later

THW Bäck, AV Kononova, B van Stein… - Evolutionary …, 2023‏ - ieeexplore.ieee.org
Thirty years, 1993–2023, is a huge time frame in science. We address some major
developments in the field of evolutionary algorithms, with applications in parameter …

On the importance of environments in human-robot coordination

MC Fontaine, YC Hsu, Y Zhang, B Tjanaka… - arxiv preprint arxiv …, 2021‏ - arxiv.org
When studying robots collaborating with humans, much of the focus has been on robot
policies that coordinate fluently with human teammates in collaborative tasks. However, less …

Multi-objective quality diversity optimization

T Pierrot, G Richard, K Beguir, A Cully - Proceedings of the Genetic and …, 2022‏ - dl.acm.org
In this work, we consider the problem of Quality-Diversity (QD) optimization with multiple
objectives. QD algorithms have been proposed to search for a large collection of both …

Illuminating diverse neural cellular automata for level generation

S Earle, J Snider, MC Fontaine, S Nikolaidis… - Proceedings of the …, 2022‏ - dl.acm.org
We present a method of generating diverse collections of neural cellular automata (NCA) to
design video game levels. While NCAs have so far only been trained via supervised …

Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers

L Yuan, Z Zhang, K Xue, H Yin, F Chen… - Proceedings of the …, 2023‏ - ojs.aaai.org
Abstract Cooperative Multi-agent Reinforcement Learning (CMARL) has shown to be
promising for many real-world applications. Previous works mainly focus on improving …

Deep surrogate assisted map-elites for automated hearthstone deckbuilding

Y Zhang, MC Fontaine, AK Hoover… - Proceedings of the …, 2022‏ - dl.acm.org
We study the problem of efficiently generating high-quality and diverse content in games.
Previous work on automated deckbuilding in Hearthstone shows that the quality diversity …