Playing Atari with Deep Reinforcement Learning Volodymyr Mnih Koray Kavukcuoglu - SARSA - Document - PDFSEARCH.IO - Document Search Engine

Back to Results

First Page	Meta Content
	Playing Atari with Deep Reinforcement Learning Volodymyr Mnih Koray Kavukcuoglu Add to Reading List Document Date: 2013-12-19 11:19:32 Open Document File Size: 423,75 KB Share Result on Facebook Company Neural Information Processing Systems / Neural Networks / MIT Press / GPU / Atari / Alex Graves Ioannis Antonoglou Martin Riedmiller DeepMind Technologies / / Facility terminal φj+1 / University of Toronto / Arcade Learning Environment / / IndustryTerm model-free reinforcement learning algorithm / evolutionary policy search approach / similar online approaches / model-free reinforcement learning algorithms / energy-based policies / convolutional networks / deep learning algorithms / reinforcement learning algorithm / deep learning applications / hand-engineered object detector algorithm / reinforcement learning algorithms / value iteration algorithms / learning algorithm / / Organization MIT / University of Toronto / / Person Pierre Sermanet / Breakout Enduro Pong / Yavar Naddaf / Martin Riedmiller / Marc Bellemare / Volodymyr Mnih / Shalabh Bhatnagar / John N Tsitsiklis / Geoffrey E. Hinton / Alan D. Blair / Mohamed / Michael Bowling / Geoffrey E Hinton / Chris Atkeson / Andrew Barto / Richard S. Sutton / David Silver / Soumith Chintala / Benjamin Van Roy / Geoff Hinton / Csaba Szepesv´ari / Breakout Enduro / Rich Sutton / Gerald Tesauro / Dong Yu / Ilya Sutskever / Morgan Kaufmann / Nicolas Heess / Sascha Lange / Peter Dayan / Andrew Moore / Matthew Hausknecht / Peter Stone / Kevin Jarrett / Marc G Bellemare / Brian Sallans / Yee Whye Teh / Hamid Maei / Vinod Nair / Doina Precup / Marc G. Bellemare / Volodymyr Mnih Koray Kavukcuoglu David / Joel Veness / Koray Kavukcuoglu / George E. Dahl / David Silver Daan Wierstra / Yann LeCun / Csaba Szepesvari / Risto Miikkulainen / / Position Rt / reward rt / human player / expert human game player / expert human player / Rider / / Product RMSProp / / PublishedMedium Machine Learning / Journal of Artificial Intelligence Research / Communications of the ACM / Journal of Machine Learning Research / / Technology previous RL algorithms / speech recognition / value iteration algorithms / RMSProp algorithm / model-free reinforcement learning algorithms / RL algorithms / Machine Learning / hand-engineered object detector algorithm / ALE / deep learning algorithms / model-free reinforcement learning algorithm / learning algorithm / reinforcement learning algorithms / RPROP algorithm / lasers / neural network / 4 Algorithm / Sarsa algorithm / reinforcement learning algorithm / Q-learning algorithm / / SocialTag Computational neuroscience Cybernetics Reinforcement learning Q-learning Temporal difference learning SARSA Markov decision process Unsupervised learning Recurrent neural network Machine learning