| Open Document File Size: 125,54 KBShare Result on Facebook
City Denver / Belmont / New York / Belmount / / Company Neural Information Processing Systems / Cambridge University Press / MIT Press / Dk / / Country Jordan / United States / United Kingdom / / / Facility Kings College / / Holiday Assumption / / IndustryTerm ǫ-optimal solution / iteration algorithm / empirical operator / well-founded reinforcement learning algorithm / max operator / indirect algorithms / value iteration algorithm / learning algorithms / / Organization Cambridge University / SC CC / MIT / Kings College / / Person Peter Auer / Mohammad Gheshlaghi Azar / Remi Munos / Mohammad Ghavamzadeh / J. Peng / R. J. Williams / / ProgrammingLanguage E / SQL / D / / ProvinceOrState New York / Massachusetts / Colorado / / PublishedMedium Machine Learning / Journal of Machine Learning Research / / Technology theoretically well-founded reinforcement learning algorithm / Speedy Q-learning algorithm / SQL algorithm / value iteration algorithm / 1 iteration algorithm / RL algorithms / learning algorithms / Machine Learning / model-based batch Q-value iteration algorithm / RL algorithm / 3.1 Speedy Q-Learning Algorithm / incremental modelfree RL algorithms / Q-learning algorithm / Phased Q-learning algorithm / mild assumptions.1 Algorithm / /
SocialTag |
Speedy Q-Learning Mohammad Gheshlaghi Azar