首页 /研究 /Active Exploration and Learning in Real-Valued Spaces using Multi-Armed Bandit Allocation Indices
OTHER

Active Exploration and Learning in Real-Valued Spaces using Multi-Armed Bandit Allocation Indices

Marcos Salganicoff, Lyle Ungar

发表年份
1995
引用次数
16

关键词

Stochastic gameTask (project management)Action (physics)Action selectionHeuristicSet (abstract data type)Computer scienceArtificial intelligenceState (computer science)Mathematical optimization

相关论文

查看 OTHER 分类全部论文