Principles of Solomonoff Induction and AIXI
From MaRDI portal
Publication:2868427
Abstract: We identify principles characterizing Solomonoff Induction by demands on an agent's external behaviour. Key concepts are rationality, computability, indifference and time consistency. Furthermore, we discuss extensions to the full AI case to derive AIXI.
Recommendations
- On the computability of Solomonoff induction and AIXI
- scientific article; zbMATH DE number 1324445
- scientific article; zbMATH DE number 4014064
- scientific article; zbMATH DE number 4074451
- scientific article; zbMATH DE number 3057873
- scientific article; zbMATH DE number 4164162
- scientific article; zbMATH DE number 4121955
- Axiomatization of Induced Theories
- scientific article; zbMATH DE number 1163362
- The Induction Axiom and the Axiom of Choice
Cited in
(6)- On the computability of Solomonoff induction and knowledge-seeking
- Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
- A Monte-Carlo AIXI approximation
- Solomonoff induction violates Nicod's criterion
- Natural descriptions and anthropic bias: extant problems in Solomonoff induction
- On the computability of Solomonoff induction and AIXI
This page was built for publication: Principles of Solomonoff Induction and AIXI
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2868427)