首页 /研究 /Undesired state-action prediction in multi-agent reinforcement learning for linked multi-component robotic system control
LEARNING

Undesired state-action prediction in multi-agent reinforcement learning for linked multi-component robotic system control

Borja Fernandez‐Gauna, Ion Marqués, Manuel Graña

发表年份
2013
引用次数
14

关键词

Reinforcement learningComponent (thermodynamics)Computer scienceArtificial intelligenceState (computer science)Action (physics)ReinforcementControl (management)Machine learningEngineering

相关论文

查看 LEARNING 分类全部论文