2
$\begingroup$

I'm trying to estimate the effect of personality on exploration behavior in multi armed bandit problems. My current approach is to identify the choice strategy that most accurately fits the behavior shown by the participants and then relate the relevant exploration parameter to the personality metric I'm using. However, I can't come up with a solution to how the first part (selecting the most fitting choice strategy) could actually be achieved in practice and Google just brings up ML related information where the agent is an algorithm and not a human being. Is there a way in which something like this is typically done?

$\endgroup$
1
  • 1
    $\begingroup$ Welcome to OR.SE. I am not familiar with the mentioned problem, but for the problems with the non-quantitive parameters or at least for the problem that the input data might not be found or estimated as a straight way, MCDM (multi-criteria decision making) would be helpful. Would you see that? $\endgroup$
    – A.Omidi
    May 30 at 13:57
1
$\begingroup$

Figured it out. It works exactly they way I originally intended to do it in my question. See this tutorial for detailed information on how to actually implement the procedure with real data.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.