In a 2-armed-bandit problem, an agent has an opportunity to see n reward for each action. Now the agent should choose actions m times and maximize the expected reward in these m decisions. but it cant see the reward of them. what is the best approach for this?

  • $\begingroup$ Could you clarify - the agent is allowed $n$ time steps where it can see the rewards, followed by $m$ time steps over which it wants to maximise the reward, but gets no further feedback? $\endgroup$ Commented Nov 23, 2020 at 20:51
  • $\begingroup$ Yes, That's right! $\endgroup$
    – lighting
    Commented Nov 24, 2020 at 4:14


You must log in to answer this question.

Browse other questions tagged .