A mathematical theory of intelligence: from defining it formally, to building the universal AIXI agent, to measuring the limits of computation. The dissertation that co-founded DeepMind.
Inductive inference, Solomonoff prior, Kolmogorov complexity, and the AIXI agent.
Passive and active environments, MDPs, POMDPs, ergodicity, and self-optimising agents.
A formal mathematical definition of machine intelligence and its properties.
Prediction complexity, hard sequences, and the Godel incompleteness barrier.
Deriving an automatic learning rate for temporal difference methods from first principles.