首页 /研究 /A policy optimization algorithm based on sample adaptive reuse and dual-clipping for robotic action control
OTHER

A policy optimization algorithm based on sample adaptive reuse and dual-clipping for robotic action control

Li-yang Zhao, Tian-qing Chang, Jie Zhang, Lei Zhang, Kai-xuan Chu, Libin Guo, Depeng Kong

发表年份
2022
引用次数
5

关键词

Computer scienceClipping (morphology)Reinforcement learningBenchmark (surveying)Stability (learning theory)Sample (material)Dual (grammatical number)Mathematical optimizationReuseAlgorithm

相关论文

查看 OTHER 分类全部论文