%0 Report %1 szepesvari2000 %A Szepesvári, Cs. %C Budapest 1121, Konkoly Th. M. u. 29-33, HUNGARY %D 2000 %K approximation approximation, asymptotic convergence, function learning, reinforcement stochastic theory, %N TR-2001-02 %T Convergent Reinforcement Learning with Value Function Interpolation %X We consider the convergence of a class of reinforcement learning algorithms combined with value function interpolation methods using the methods developed in (Littman and Szepesvari, 1996). As a special case of the obtained general results, for the first time, we prove the (almost sure) convergence of Q-learning when combined with value function interpolation in uncountable spaces.

@techreport{szepesvari2000, abstract = {We consider the convergence of a class of reinforcement learning algorithms combined with value function interpolation methods using the methods developed in (Littman and Szepesvari, 1996). As a special case of the obtained general results, for the first time, we prove the (almost sure) convergence of Q-learning when combined with value function interpolation in uncountable spaces.}, added-at = {2020-03-17T03:03:01.000+0100}, address = {Budapest 1121, Konkoly Th. M. u. 29-33, HUNGARY}, author = {Szepesv{\'a}ri, {Cs}.}, biburl = {https://www.bibsonomy.org/bibtex/2544e8cd1eb7d6f727d08056084571333/csaba}, date-modified = {2010-09-04 14:48:33 -0600}, institution = {Mindmaker Ltd.}, interhash = {8e8d2861537563c0465f7d92f2473b12}, intrahash = {544e8cd1eb7d6f727d08056084571333}, keywords = {approximation approximation, asymptotic convergence, function learning, reinforcement stochastic theory,}, number = {TR-2001-02}, pdf = {papers/rlfapp.pdf}, timestamp = {2020-03-17T03:03:01.000+0100}, title = {Convergent Reinforcement Learning with Value Function Interpolation}, year = 2000 }