<abstract xmlns="http://www.w3.org/1999/xhtml"><p>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.</p></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.

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

Journal of Artificial General Intelligence

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

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...

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

Data publikacji: 15 paź 2020

Zakres stron: 70 - 85

Otrzymano: 16 lut 2020

Przyjęty: 29 wrz 2020

DOI: https://doi.org/10.2478/jagi-2020-0004

© 2020 Samuel Allen Alexander, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.