Biological neural networks are systems of extraordinary computational capabilities shaped
by evolution, development, and lifelong learning. The interplay of these elements leads to …

Evolutionary computation is inspired by the mechanisms of biological evolution. With
algorithmic improvements and increasing computing resources, evolutionary computation …

Accurate reporting of energy and carbon usage is essential for understanding the potential
climate impacts of machine learning research. We introduce a framework that makes this …

Reinforcement learning algorithms rely on carefully engineering environment rewards that
are extrinsic to the agent. However, annotating each environment with hand-designed …

Intrinsically motivated spontaneous exploration is a key enabler of autonomous
developmental learning in human children. It enables the discovery of skill repertoires …

In many text-generation problems, users may prefer not only a single response, but a
diverse range of high-quality outputs from which to choose. Quality-diversity (QD) search …

Perhaps the most ambitious scientific quest in human history is the creation of general
artificial intelligence, which roughly means AI that is as smart or smarter than humans. The …

As large language models (LLMs) become increasingly prevalent across many real-world
applications, understanding and enhancing their robustness to user inputs is of paramount …

Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast
environment search space, but there are thus infinitely many possible tasks. Even after …

Optimization is about finding the best available object with respect to an objective function.
Mathematics and quantitative sciences have been highly successful in formulating problems …