首页 /研究 /Reinforcement Learning endowed with safe veto policies to learn the control of Linked-Multicomponent Robotic Systems
LEARNING

Reinforcement Learning endowed with safe veto policies to learn the control of Linked-Multicomponent Robotic Systems

Borja Fernandez‐Gauna, Manuel Graña, José Manuel López-Guede, Ismael Etxeberria‐Agiriano, Igor Ansoategui

发表年份
2015
引用次数
13

关键词

Reinforcement learningComputer scienceState spaceProcess (computing)State (computer science)Modular designConvergence (economics)Artificial intelligenceControl (management)Task (project management)

相关论文

查看 LEARNING 分类全部论文