Nature

Improved double DQN with deep reinforcement learning for UAV indoor autonomous obstacle ...

Aiming at the problems of insufficient autonomous obstacle avoidance performance of UAVs in complex indoor environments, an improved Double DQN algorithm based on deep reinforcement learning is ...
iNSIDE

Google、ゲームを自己学習する人工知能を開発―脅威の「DQN ...

昨年Googleによって買収された人工知能開発会社Deep Mind。同社が開発した「自らゲームルールを学習する人工知能（以下AI）」の驚くべき成果が英科学誌ネイチャーで発表され、話題になっています。 話題となっているのは「Deep Q-Network(以下DQN)」アルゴリズム ...
Nature

A social network graph partitioning algorithm based on double deep Q-Network

In recent years, with the rapid development of technologies such as mobile internet, the internet of things, social networks, and big data processing, various industries have begun to generate vast ...
GIGAZINE

"DQN" and three kinds of variations of reinforcement learning algorithm published by ...

"DQN" and three kinds of variations of reinforcement learning algorithm published by Artificial intelligence research organization "OpenAI" Known as the founder of Tesla and SpaceX Earlon mask Mr. is ...
GIGAZINE

「DQN」とその3種のバリエーションの強化学習アルゴリズムを人工 ...

テスラやSpaceXの創業者として知られるイーロン・マスク氏は、人工知能(AI)の非営利団体「OpenAI」の設立にも携わっています。このOpenAIが、強化学習アルゴリズム(RLアルゴリズム)の高品質な実装である「OpenAI Baselines」のうち、Deep Q-Learning(DQN)と3種類の ...