Problems of Self-reference in Self-improving Space-Time Embedded Intelligence

Autor:	Nate Soares, Benja Fallenstein
Rok vydání:	2014
Předmět:	Computer science business.industry media_common.quotation_subject Space time Procrastination Embedded intelligence Gödel's incompleteness theorems Artificial intelligence situated approach Formalism (philosophy of mathematics) Obstacle Self-reference Artificial intelligence business media_common
Zdroj:	Artificial General Intelligence ISBN: 9783319092737 AGI
DOI:	10.1007/978-3-319-09274-4_3
Popis:	By considering agents to be a part of their environment, Orseau and Ring’s space-time embedded intelligence [10] is a better fit to the real world than the traditional agent framework. However, a self-modifying AGI that sees future versions of itself as an ordinary part of the environment may run into problems of self-reference. We show that in one particular model based on formal logic, naive approaches either lead to incorrect reasoning that allows an agent to put off an important task forever (the procrastination paradox), or fail to allow the agent to justify even obviously safe rewrites (the Lobian obstacle). We argue that these problems have relevance beyond our particular formalism, and discuss partial solutions.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::e0f3f2cad8970cfd5d5f7faf059e143f https://doi.org/10.1007/978-3-319-09274-4_3 Zobrazit plný text záznamu