General Purpose Artificial Intelligence Systems (GPAIS): Properties, definition, taxonomy, societal implications and responsible governance
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 …
specific task. However, there are many scenarios that call for a more general AI, capable of …
Differentiable quality diversity
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 …
problem of generating an archive of solutions that maximize a given objective function but …
pyribs: A bare-bones python library for quality diversity optimization
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 …
branch of optimization that seeks to find a collection of diverse, high-performing solutions to …
Goals as reward-producing programs
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 …
and continuing into adulthood. Despite considerable empirical and computational work on …
Evolutionary algorithms for parameter optimization—thirty years later
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 …
developments in the field of evolutionary algorithms, with applications in parameter …
On the importance of environments in human-robot coordination
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 …
policies that coordinate fluently with human teammates in collaborative tasks. However, less …
Multi-objective quality diversity optimization
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 …
objectives. QD algorithms have been proposed to search for a large collection of both …
Illuminating diverse neural cellular automata for level generation
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 …
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
Abstract Cooperative Multi-agent Reinforcement Learning (CMARL) has shown to be
promising for many real-world applications. Previous works mainly focus on improving …
promising for many real-world applications. Previous works mainly focus on improving …
Deep surrogate assisted map-elites for automated hearthstone deckbuilding
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 …
Previous work on automated deckbuilding in Hearthstone shows that the quality diversity …