We present the first deep learning model to successfully learn control
policies directly from high-dimensional sensory input using reinforcement
learning. The model is a convolutional neural network, trained with a variant
of Q-learning, whose input is raw pixels and whose output is a value function
estimating future rewards. We apply our method to seven Atari 2600 games from
the Arcade Learning Environment, with no adjustment of the architecture or
learning algorithm. We find that it outperforms all previous approaches on six
of the games and surpasses a human expert on three of them.
Please log in to take part in the discussion (add own reviews or comments).
Cite this publication
More citation styles
- please select -
%0 Journal Article
%1 mnih2013atari
%A Mnih, Volodymyr
%A Kavukcuoglu, Koray
%A Silver, David
%A Graves, Alex
%A Antonoglou, Ioannis
%A Wierstra, Daan
%A Riedmiller, Martin
%D 2013
%K
%T Playing Atari with Deep Reinforcement Learning
%U http://arxiv.org/abs/1312.5602
%X We present the first deep learning model to successfully learn control
policies directly from high-dimensional sensory input using reinforcement
learning. The model is a convolutional neural network, trained with a variant
of Q-learning, whose input is raw pixels and whose output is a value function
estimating future rewards. We apply our method to seven Atari 2600 games from
the Arcade Learning Environment, with no adjustment of the architecture or
learning algorithm. We find that it outperforms all previous approaches on six
of the games and surpasses a human expert on three of them.
@article{mnih2013atari,
abstract = {We present the first deep learning model to successfully learn control
policies directly from high-dimensional sensory input using reinforcement
learning. The model is a convolutional neural network, trained with a variant
of Q-learning, whose input is raw pixels and whose output is a value function
estimating future rewards. We apply our method to seven Atari 2600 games from
the Arcade Learning Environment, with no adjustment of the architecture or
learning algorithm. We find that it outperforms all previous approaches on six
of the games and surpasses a human expert on three of them.},
added-at = {2019-07-12T20:11:01.000+0200},
author = {Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Graves, Alex and Antonoglou, Ioannis and Wierstra, Daan and Riedmiller, Martin},
biburl = {https://www.bibsonomy.org/bibtex/2a00ec4c09f5dc9b3f8a1836f4e02bb5d/lanteunis},
interhash = {78966703f649bae69a08a6a23a4e8879},
intrahash = {a00ec4c09f5dc9b3f8a1836f4e02bb5d},
keywords = {},
note = {cite arxiv:1312.5602Comment: NIPS Deep Learning Workshop 2013},
timestamp = {2019-07-12T20:11:01.000+0200},
title = {Playing Atari with Deep Reinforcement Learning},
url = {http://arxiv.org/abs/1312.5602},
year = 2013
}