Principles of Solomonoff Induction and AIXI
Peter Sunehag, Marcus Hutter
TL;DR
This paper explores the foundational principles behind Solomonoff Induction and AIXI, emphasizing rationality, computability, indifference, and time consistency to characterize optimal decision-making in artificial intelligence.
Contribution
It formalizes principles characterizing Solomonoff Induction and extends them to derive the AIXI model for general AI.
Findings
Identifies key principles for Solomonoff Induction
Discusses extensions to full AI for AIXI derivation
Highlights the importance of rationality and computability
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputability, Logic, AI Algorithms · Logic, Reasoning, and Knowledge · AI-based Problem Solving and Planning