AIXI

On Intelligence: The Gap Where Safety Is Decided

There is a beautiful, settled theory of intelligence, and there are the crude systems we shipped. The distance between them is where safety is actually decided.

Reinforcement Learning Is Cross-Entropy, Reweighted by Reward

When the only signal is a number at the end of a trajectory. How REINFORCE turns out to be the same gradient as classification, scaled by return, and where the theory tops out.

On Intelligence: and Its Specifications

We taught sand to think. We did it before we learned to say what we wanted it to do. There is a real, settled, and genuinely beautiful theory of what intelligence is: Bayes' theorem, Solomonoff's universal prior, and expected-utility maximization, …

What You Assume vs. What You Compute

Part 4 of What Your RL Algorithm Actually Assumes — model-based vs. model-free, the assumptions table, AIXI as the incomputable ideal, and the unifying claim: representation is prior is assumption.

An Introduction to Universal Artificial Intelligence

Notes

Newer textbook presenting AIXI and related universal agent theory with updated structure; suitable after the core UAI book.

Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI

Notes

Lecture on AIXI and universal intelligence theory with deep insights.

Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability

Notes

Formal theory of universal agents combining Solomonoff induction and sequential decision theory; foundational for AGI theory.