View topic on PhilPapers for more information
Related categories

1 found
More results on PhilPapers
  1. Reward-Punishment Symmetric Universal Intelligence.Samuel Allen Alexander & Marcus Hutter - forthcoming - In AGI-21.
    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.
    Remove from this list   Download  
    Export citation