Reward-Punishment Symmetric Universal Intelligence

In AGI (2021)
  Copy   BIBTEX


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.

Author Profiles

Samuel Allen Alexander
Ohio State University (PhD)
Marcus Hutter
Australian National University


Added to PP

177 (#55,616)

6 months
49 (#42,174)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?