Principles of Solomonoff Induction and AIXI
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.
|Collections||ANU Research Publications|
|Sunehag and Hutter Principles of Solomonoff Induction 2011.pdf||117.6 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.