Deep Reinforcement Learning with Risk-Seeking Exploration

Nat Dilokthanakul
Nat Dilokthanakul

SAB, pp. 201-211, 2018.

被引用0|引用|浏览2|来源
EI

摘要

In most contemporary work in deep reinforcement learning (DRL), agents are trained in simulated environments. Not only are simulated environments fast and inexpensive, they are also ‘safe’. By contrast, training in a real world environment (using robots, for example) is not only slow and costly, but actions can also result in irreversible...更多

代码

数据

您的评分 :
0

 

标签
评论