In Sutton and Barto's reinforcement learning book, in multi-armed bandit problem a phrase has been used. "finding an optimal action" using greedy/$\epsilon$-greedy algorithm. When it is said that an algorithm "finds the optimal action " ?


In the bandit setting, to each arm is associated an unknown reward distribution. The optimization goal is to find a policy (a series of level pulls) which yields the maximum sum of rewards.

"Finding an optimal action" thus refers to the process of discovering the arm which gives you the most reward.

| cite | improve this answer | |
  • $\begingroup$ what is that process ? sampling is used to estimate the mean. so how to tell at which step I have found the optimal action ? $\endgroup$ – RIchard Williams May 1 '14 at 13:58
  • $\begingroup$ At which step: this is algorithm-specific. Some methods might provide some bounds, but in general I would say that you run you algorithm until it's "good enough". $\endgroup$ – Pierre-Luc Bacon May 6 '14 at 21:08

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.