Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning 论文

2004Journal of Machine Learning Research引用 323
DOI
Reinforcement Learning in RoboticsAdaptive Dynamic Programming ControlAdvanced Bandit Algorithms Research
机器人Reinforcement Learning in RoboticsAdvanced Bandit Algorithms ResearchAdaptive Dynamic Programming Control
相关技术:Reinforcement Learning in RoboticsAdvanced Bandit Algorithms Research
关系图谱

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning · 相关技术

相关技术

Reinforcement Learning in RoboticsAdvanced Bandit Algorithms Research