首页 /研究 /Policy Gradients with Parameter-Based Exploration for Control
OTHER

Policy Gradients with Parameter-Based Exploration for Control

Frank Sehnke, Christian Osendorfer, Thomas Rückstieß, Alex Graves, Jan Peters, Jürgen Schmidhuber

发表年份
2008
引用次数
60

关键词

Computer scienceReinforcement learningHeuristicsHumanoid robotMarkov decision processSampling (signal processing)Mathematical optimizationVariance (accounting)PopulationMarkov chain

相关论文

查看 OTHER 分类全部论文