%0 Book Section %1 szepesvari2010 %A Szepesvári, Cs. %B Wiley Encyclopedia of Operations Research %D 2010 %I Wiley %K Monte-Carlo PAC-learning, Q-learning, active actor-critic approximation, bias-variance difference function gradient gradient, learning, least-squares methods, natural online optimization, overfitting, planning, policy reinforcement simulation simulation, stochastic survey, temporal tradeoff, two-timescale %T Reinforcement Learning Algorithms for MDPs

@incollection{szepesvari2010, added-at = {2020-03-17T03:03:01.000+0100}, author = {Szepesv{\'a}ri, {Cs}.}, biburl = {https://www.bibsonomy.org/bibtex/2a4a1e00b2ef2fe32753026aa116df1b9/csaba}, booktitle = {Wiley Encyclopedia of Operations Research}, date-added = {2010-08-28 20:43:59 -0600}, date-modified = {2010-11-25 00:42:56 -0700}, interhash = {70bf2efe930e5462087705c218a2e410}, intrahash = {a4a1e00b2ef2fe32753026aa116df1b9}, keywords = {Monte-Carlo PAC-learning, Q-learning, active actor-critic approximation, bias-variance difference function gradient gradient, learning, least-squares methods, natural online optimization, overfitting, planning, policy reinforcement simulation simulation, stochastic survey, temporal tradeoff, two-timescale}, month = {September}, publisher = {Wiley}, timestamp = {2020-03-17T03:03:01.000+0100}, title = {Reinforcement Learning Algorithms for MDPs}, year = 2010 }