Live briefing
Everything about AIXI
Mathematical formalism for artificial general intelligence
AIXI is a theoretical mathematical formalism for artificial general intelligence. It combines Solomonoff induction with sequential decision theory. AIXI was first proposed by Marcus Hutter in 2000 and several results regarding AIXI are proved in Hutter's 2005 book Universal Artificial Intelligence. Wikipedia →
🧠Start here: a 6-step reading path
- Read the overview: AIXIA 5-minute orientation
- Pick up a classic book: This Is How You Lose HerThe most-reprinted book on the subject
- Read the landmark paper: A Monte-Carlo AIXI ApproximationCited 75 times
- Go sideways: Algorithmic probabilityA closely related topic
- Go sideways: Kernel embedding of distributionsA closely related topic
đź“– Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
đź“š Books worth reading
This Is How You Lose HerJunot DĂaz · 2012
E' stato cosìNatalia Ginzburg · 1949
AntifeixistesMiquel Ramos · 2022
AixĂ mengen els animalsPetra BartĂková, KatarĂna Macurová · 2020- đź“•Applied Engineering ExperimentsAixi Zhou · 2021
- 📕Animal Homes (Secrets of Nature)Sarah Waters · 1993
- đź“•D'equivocar-se aixĂEnric Casassas Figueres · 1997
- 📕Per què soc aix�Juli Capella · 2022
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
đź”— Related topics
- Algorithmic probability In algorithmic information theory, algorithmic probability, also known as Solomonoff probability, is a mathematical method of assigning a prior probability…
- Kernel embedding of distributions In machine learning, the kernel embedding of distributions (also called the kernel mean or mean map) comprises a class of nonparametric methods in which…
- Kullback–Leibler Upper Confidence Bound In multi-armed bandit problems, KL-UCB (for Kullback–Leibler Upper Confidence Bound) is a UCB-type algorithm that is asymptotically optimal, in the sense…
- Next-bit test In cryptography and the theory of computation, the next-bit test is a test against pseudo-random number generators. We say that a sequence of bits passes…
- Stochastic game In game theory, a stochastic game (or Markov game) is a repeated game with probabilistic transitions played by one or more players. The game is played…
- Karush–Kuhn–Tucker conditions In mathematical optimization, the Karush–Kuhn–Tucker (KKT) conditions, also known as the Kuhn–Tucker conditions, are first derivative tests (sometimes…
- Thompson sampling Thompson sampling, named after William Rae Thompson, is a heuristic for choosing actions that address the exploration–exploitation dilemma in the multi-armed…
- Gödel machine A Gödel machine is a hypothetical self-improving computer program that solves problems in an optimal way. It uses a recursive self-improvement protocol…