The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI

Download Edit this record How to cite View on PhilPapers
Abstract
After generalizing the Archimedean property of real numbers in such a way as to make it adaptable to non-numeric structures, we demonstrate that the real numbers cannot be used to accurately measure non-Archimedean structures. We argue that, since an agent with Artificial General Intelligence (AGI) should have no problem engaging in tasks that inherently involve non-Archimedean rewards, and since traditional reinforcement learning rewards are real numbers, therefore traditional reinforcement learning probably will not lead to AGI. We indicate two possible ways traditional reinforcement learning could be altered to remove this roadblock.
PhilPapers/Archive ID
ALETAT-12
Upload history
First archival date: 2020-02-15
Latest version: 2 (2020-10-20)
View other versions
Added to PP index
2020-02-15

Total views
9,471 ( #116 of 54,342 )

Recent downloads (6 months)
9,234 ( #8 of 54,342 )

How can I increase my downloads?

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