%0 Conference Paper %1 szepesvari1997h %A Szepesvári, Cs. %B ECML %D 1997 %E Someren, M.van %E Widmer, G. %I Springer, Berlin %K exploitation, exploration learning, reinforcement theory vs. %P 242--249 %T Learning and Exploitation do not Conflict Under Minimax Optimality %V 1224 %X We show that adaptive real time dynamic programming extended with the action selection strategy which chooses the best action according to the latest estimate of the cost function yields asymptotically optimal policies within finite time under the minimax optimality criterion. From this it follows that learning and exploitation do not conflict under this special optimality criterion. We relate this result to learning optimal strategies in repeated two-player zero-sum deterministic games.

@inproceedings{szepesvari1997h, abstract = {We show that adaptive real time dynamic programming extended with the action selection strategy which chooses the best action according to the latest estimate of the cost function yields asymptotically optimal policies within finite time under the minimax optimality criterion. From this it follows that learning and exploitation do not conflict under this special optimality criterion. We relate this result to learning optimal strategies in repeated two-player zero-sum deterministic games.}, added-at = {2020-03-17T03:03:01.000+0100}, author = {Szepesv{\'a}ri, {Cs}.}, biburl = {https://www.bibsonomy.org/bibtex/2bf0cdbf8f95dcf569cc94228faa69fa4/csaba}, booktitle = {ECML}, date-added = {2010-08-28 17:38:14 -0600}, date-modified = {2010-11-25 00:57:05 -0700}, editor = {Someren, M.{van} and Widmer, G.}, interhash = {696679de5080b1e6b8698dbe0d18fc1a}, intrahash = {bf0cdbf8f95dcf569cc94228faa69fa4}, keywords = {exploitation, exploration learning, reinforcement theory vs.}, pages = {242--249}, pdf = {papers/ecml97.ps.pdf}, publisher = {Springer, Berlin}, series = {Lecture Notes in Artificial Intelligence}, timestamp = {2020-03-17T03:03:01.000+0100}, title = {Learning and Exploitation do not Conflict Under Minimax Optimality}, volume = 1224, year = 1997 }