• What is “useful?”
  • Choose from several options that you think would be “useful
  • We know that the knowledge that produced the choice is useful when, after choosing and executing it, posterior we actually obtain a useful result.
    • I thought it needed a little work because it was circular referencing, but I also felt that it would be good if it was useful even if it was circular referencing.

relevance - reinforcement learning - intersubjective


This page is auto-translated from /nishio/有用 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.