Shane Legg

TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

TL;DR: A new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) is developed that not only uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation.

TL;DR: A number of well known informal definitions of human intelligence are taken, and mathematically formalised to produce a general measure of intelligence for arbitrary machines that formally captures the concept of machine intelligence in the broadest reasonable sense.

TL;DR: It is found that replacing the conventional exploration heuristics for A3C, DQN and dueling agents with NoisyNet yields substantially higher scores for a wide range of Atari games, in some cases advancing the agent from sub to super-human performance.

TL;DR: In this paper, the authors take a number of well known informal definitions of human intelligence and extract their essential features, which are then mathematically formalised to produce a general measure of intelligence for arbitrary machines, and show how this formal definition is related to the theory of universal optimal learning agents.