Playing Atari with Deep Reinforcement Learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · arXiv (Cornell University) · 2013
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.
Cited by 4,728 works. doi:10.48550/arxiv.1312.5602 Open-access PDF
Authors
- Volodymyr Mnih
- Koray Kavukcuoglu
- David Silver
- Alex Graves
- Ioannis Antonoglou
- Daan Wierstra
- Martin Riedmiller
References
- ImageNet classification with deep convolutional neural networks
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Reinforcement Learning: An Introduction
- What is the best multi-stage architecture for object recognition?
- Speech recognition with deep recurrent neural networks
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
- Convolutional networks for images, speech, and time series
- Pedestrian Detection with Unsupervised Multi-stage Feature Learning
- Temporal difference learning and TD-Gammon
- An analysis of temporal-difference learning with function approximation