SOTAVerified

Playing Atari with Deep Reinforcement Learning

2013-12-19Code Available1· sign in to hype

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

Atari GamesDeep Reinforcement LearningMulti-Goal Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
Atari 2600 Beam RiderDQN BestScore5,184—Unverified
Atari 2600 BreakoutDQN BestScore225—Unverified
Atari 2600 EnduroDQN BestScore661—Unverified
Atari 2600 PongDQN BestScore21—Unverified
Atari 2600 Q*BertDQN BestScore4,500—Unverified
Atari 2600 SeaquestDQN BestScore1,740—Unverified
Atari 2600 Space InvadersDQN BestScore1,075—Unverified

Reproductions