A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning

Fanghui Huang, Xinyang Deng, Yixin He, Wen Jiang

科研成果: 期刊稿件 › 文章 › 同行评审

13 引用 （Scopus）

指纹

探究 'A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning' 的科研主题。它们共同构成独一无二的指纹。

Computer Science