A fundamental problem in artificial intelligence is that nobody really knows what intelligence
is. The problem is especially acute when we need to consider artificial systems which are …

Reinforcement learning agents have demonstrated remarkable achievements in simulated
environments. Data efficiency poses an impediment to carrying this success over to real …

The evaluation of artificial intelligence systems and components is crucial for the progress of
the discipline. In this paper we describe and critically assess the different ways AI systems …

This book is designed to become a foundational text for the new science of AI safety
engineering. While specific predictions regarding the consequences of an intelligence …

Uncertainty is an epistemological concept in the sense that any meaningful understanding of
uncertainty requires a theory of knowledge. Therefore, uncertainty resulting from scientific …

This paper introduces a principled approach for the design of a scalable general
reinforcement learning agent. Our approach is based on a direct approximation of AIXI, a …

In this paper, we develop the idea of a universal anytime intelligence test. The meaning of
the terms “universal” and “anytime” is manifold here: the test should be able to measure the …

An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills
over a long lifetime could advance the frontier of artificial intelligence capabilities. The …

We are at the cusp of a transition from 'learning from data'to 'learning what data to learn
from'as a central focus of artificial intelligence (AI) research. While the first-order learning …

Artificial General Intelligence seeks to create an artificial system capable of solving many
different and possibly unforeseen tasks thus being comparable in its intelligence to that of a …