Switch to: References

Add citations

You must login to add citations.
  1. Extending Environments To Measure Self-Reflection In Reinforcement Learning.Samuel Allen Alexander, Michael Castaneda, Kevin Compher & Oscar Martinez - manuscript
    We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things the environment's outputs are based on, we argue that for an agent to achieve on-average good performance across many such extended environments, it is necessary for the agent to self-reflect. Thus, an agent's self-reflection ability can be numerically estimated by running the agent through a battery (...)
    Download  
     
    Export citation  
     
    Bookmark  
  • The Archimedean Trap: Why Traditional Reinforcement Learning Will Probably Not Yield AGI.Samuel Allen Alexander - 2020 - Journal of Artificial General Intelligence 11 (1):70-85.
    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 (...)
    Download  
     
    Export citation  
     
    Bookmark   1 citation  
  • Measuring Intelligence and Growth Rate: Variations on Hibbard's Intelligence Measure.Samuel Alexander & Bill Hibbard - 2021 - Journal of Artificial General Intelligence 12 (1):1-25.
    In 2011, Hibbard suggested an intelligence measure for agents who compete in an adversarial sequence prediction game. We argue that Hibbard’s idea should actually be considered as two separate ideas: first, that the intelligence of such agents can be measured based on the growth rates of the runtimes of the competitors that they defeat; and second, one specific (somewhat arbitrary) method for measuring said growth rates. Whereas Hibbard’s intelligence measure is based on the latter growth-rate-measuring method, we survey other methods (...)
    Download  
     
    Export citation  
     
    Bookmark