Playing Atari with Deep Reinforcement Learning

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.

Keywords

Reinforcement learningComputer scienceArtificial intelligenceConvolutional neural networkDeep learningFunction (biology)Bellman equationValue (mathematics)ArchitectureControl (management)Machine learningPixelQ-learningReinforcementMathematicsEngineeringMathematical optimization

Related Publications

Massively Parallel Methods for Deep Reinforcement Learning

Arun Sukumaran Nair , P. Srinivasan , Sam Blackwell +11 more

We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour...

2015 arXiv (Cornell University) 405 citations

Sigmoid-weighted linear units for neural network function approximation in reinforcement learning

Stefan Elfwing , Eiji Uchibe , Kenji Doya

In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level hu...

2018 Neural Networks 1643 citations

Deep Reinforcement Learning with Double Q-Learning

Hado van Hasselt , Arthur Guez , David Silver

The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are comm...

2016 Proceedings of the AAAI Conference on... 3514 citations

Asynchronous Methods for Deep Reinforcement Learning

Volodymyr Mnih , Adrià Puigdomènech Badia , Mehdi Mirza +5 more

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network contro...

2016 arXiv (Cornell University) 1690 citations

Reinforcement Learning with Unsupervised Auxiliary Tasks

Max Jaderberg , Volodymyr Mnih , Wojciech Marian Czarnecki +4 more

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possibl...

2016 arXiv (Cornell University) 271 citations

Publication Info

Year: 2013
Type: preprint
Citations: 5109
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Playing Atari with Deep Reinforcement Learning

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

5109

OpenAlex

Cite This

APA Style

                            
                                    Volodymyr Mnih, 
                                
                                    Koray Kavukcuoglu, 
                                
                                    David Silver
                                
                                et al.
                            
                            (2013). 
                            Playing Atari with Deep Reinforcement Learning. 
                            arXiv (Cornell University)
                            
                            .
                            https://doi.org/10.48550/arxiv.1312.5602

Identifiers

DOI: 10.48550/arxiv.1312.5602