Reward-Punishment Symmetric Universal Intelligence

In AGI-21 (forthcoming)
Download Edit this record How to cite View on PhilPapers
Abstract
Can an agent's intelligence level be negative? We extend the Legg-Hutter agent-environment framework to include punishments and argue for an affirmative answer to that question. We show that if the background encodings and Universal Turing Machine (UTM) admit certain Kolmogorov complexity symmetries, then the resulting Legg-Hutter intelligence measure is symmetric about the origin. In particular, this implies reward-ignoring agents have Legg-Hutter intelligence 0 according to such UTMs.
PhilPapers/Archive ID
ALERSU
Upload history
Archival date: 2021-10-06
View other versions
Added to PP index
2021-10-06

Total views
91 ( #53,201 of 70,145 )

Recent downloads (6 months)
35 ( #24,557 of 70,145 )

How can I increase my downloads?

Downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.