Human-level control through deep reinforcement learning

Volodymyr Mnih(Google (United Kingdom)), Koray Kavukcuoglu(DeepMind (United Kingdom)), David Silver(DeepMind (United Kingdom)), Andrei A. Rusu(DeepMind (United Kingdom)), Joel Veness(Google (United Kingdom)), Marc G. Bellemare(DeepMind (United Kingdom)), Alex Graves(Google (United Kingdom)), Martin Riedmiller(DeepMind (United Kingdom)), Andreas Fidjeland(Google (United Kingdom)), Georg Ostrovski(Google (United Kingdom)), Stig Petersen(DeepMind (United Kingdom)), Charles Beattie(DeepMind (United Kingdom)), Amir Sadik(DeepMind (United Kingdom)), Ioannis Antonoglou(Google (United Kingdom)), Helen King(DeepMind (United Kingdom)), Dharshan Kumaran(DeepMind (United Kingdom)), Daan Wierstra(Google (United Kingdom)), Shane Legg(DeepMind (United Kingdom)), Demis Hassabis(DeepMind (United Kingdom))
Nature
February 24, 2015
10.1038/nature14236
Cited by 29,716

Abstract

Related Papers

Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al.|Proceedings of the IEEE|1998|57.9k
Reducing the Dimensionality of Data with Neural Networks
Geoffrey E. Hinton, Ruslan Salakhutdinov|Science|2006|20.9k
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair, Geoffrey E. Hinton|International Conference on Machine Learning|2010|13.2k
Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory.
James L. McClelland, Bruce L. McNaughton, Randall C. O’Reilly|Psychological Review|1995|5.3k
Learning Deep Architectures for AI
Yoshua Bengio|now publishers, Inc. eBooks|2009|5.1k