AIXI model
E774590
idealized reinforcement learning agent
theoretical model of artificial intelligence
uncomputable agent model
universal artificial intelligence model
The AIXI model is a theoretical framework for an idealized, maximally intelligent reinforcement learning agent that combines Solomonoff induction with sequential decision theory.
All labels observed (7)
| Label | Occurrences |
|---|---|
| AIXI | 3 |
| AIXI model canonical | 3 |
| A Monte Carlo AIXI Approximation | 1 |
| AIXI as a theoretical optimal agent | 1 |
| AIXI formalism | 1 |
| AIXI framework | 1 |
| AIXI-tl | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T9062787 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AIXI model Context triple: [Marcus Hutter, knownFor, AIXI model]
-
A.
Universal Intelligence: A Definition of Machine Intelligence
"Universal Intelligence: A Definition of Machine Intelligence" is a foundational paper by Shane Legg (with Marcus Hutter) that formally defines and mathematically characterizes general machine intelligence using concepts from algorithmic information theory and reinforcement learning.
-
B.
universal intelligence measure
The universal intelligence measure is a formal, mathematical framework proposed to quantify and compare the general intelligence of agents across all possible environments.
-
C.
Soar cognitive architecture
The Soar cognitive architecture is a general-purpose framework for modeling and understanding human cognition through unified theories of problem solving, learning, and decision-making.
-
D.
Adept AI
Adept AI is an artificial intelligence research and product company focused on building AI agents that can use existing software tools to perform complex tasks for users.
-
E.
Helmholtz machine
The Helmholtz machine is a pioneering generative neural network model that learns internal representations by using separate recognition and generative pathways to perform unsupervised learning.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AIXI model Target entity description: The AIXI model is a theoretical framework for an idealized, maximally intelligent reinforcement learning agent that combines Solomonoff induction with sequential decision theory.
-
A.
Universal Intelligence: A Definition of Machine Intelligence
"Universal Intelligence: A Definition of Machine Intelligence" is a foundational paper by Shane Legg (with Marcus Hutter) that formally defines and mathematically characterizes general machine intelligence using concepts from algorithmic information theory and reinforcement learning.
-
B.
universal intelligence measure
The universal intelligence measure is a formal, mathematical framework proposed to quantify and compare the general intelligence of agents across all possible environments.
-
C.
Soar cognitive architecture
The Soar cognitive architecture is a general-purpose framework for modeling and understanding human cognition through unified theories of problem solving, learning, and decision-making.
-
D.
Adept AI
Adept AI is an artificial intelligence research and product company focused on building AI agents that can use existing software tools to perform complex tasks for users.
-
E.
Helmholtz machine
The Helmholtz machine is a pioneering generative neural network model that learns internal representations by using separate recognition and generative pathways to perform unsupervised learning.
- F. None of above. chosen
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
idealized reinforcement learning agent
ⓘ
theoretical model of artificial intelligence ⓘ uncomputable agent model ⓘ universal artificial intelligence model ⓘ |
| assumes | unknown but computable environment ⓘ |
| basedOn |
Bayesian decision theory
ⓘ
Solomonoff induction ⓘ sequential decision theory ⓘ |
| computabilityStatus | uncomputable ⓘ |
| decisionCriterion | Bayes-optimality with respect to universal prior ⓘ |
| definedBy | Marcus Hutter ⓘ |
| environmentClass | all lower semicomputable semimeasures ⓘ |
| formalizedIn | universal artificial intelligence framework ⓘ |
| formalizes | Legg-Hutter intelligence measure ⓘ |
| goal | maximization of cumulative reward ⓘ |
| hasApproximation |
AIXItl
ⓘ
MC-AIXI-CTW ⓘ |
| hasLimitation |
depends on choice of reference universal Turing machine
ⓘ
not directly implementable on real hardware ⓘ |
| hasProperty |
defined for general reinforcement learning environments
ⓘ
environment-agnostic ⓘ maximally intelligent in its formal setting ⓘ model-free in the usual RL sense ⓘ not computable in practice ⓘ theoretically optimal ⓘ uses a universal Turing machine prior ⓘ uses algorithmic probability ⓘ |
| influenced |
formal definitions of intelligence
ⓘ
theoretical research in AGI ⓘ |
| interactionPattern | agent-environment loop ⓘ |
| introducedInWork | Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability ⓘ |
| optimizes | expected discounted reward ⓘ |
| outputs | actions to environment ⓘ |
| publicationYear | 2005 ⓘ |
| receives |
observations from environment
ⓘ
rewards from environment ⓘ |
| relatedTo |
Kolmogorov complexity
ⓘ
Solomonoff universal distribution ⓘ
linked to:
Solomonoff induction
algorithmic information theory ⓘ partially observable Markov decision processes ⓘ reinforcement learning ⓘ sequential decision processes ⓘ |
| requires |
enumeration of all programs on a universal Turing machine
ⓘ
infinite computational resources ⓘ |
| selects | actions to maximize expected future reward ⓘ |
| timeStructure | discrete time interaction cycles ⓘ |
| upperBoundFor | intelligence of computable agents in its setting ⓘ |
| uses |
Solomonoff universal prior
ⓘ
linked to:
Solomonoff induction
expectimax planning over all computable environments ⓘ mixture over all semicomputable probability measures ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: AIXI model Description of subject: The AIXI model is a theoretical framework for an idealized, maximally intelligent reinforcement learning agent that combines Solomonoff induction with sequential decision theory.
Referenced by (11)
Full triples — surface form annotated when it differs from this entity's canonical label.
linked to: AIXI model
linked to: AIXI model
linked to: AIXI model
linked to: AIXI model
Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability
→
describes
→
AIXI as a theoretical optimal agent
ⓘ
linked to: AIXI model
linked to: AIXI model
linked to: AIXI model
linked to: AIXI model