[2014] [DPG] [Deterministic Policy Gradient Algorithms]
![[2014] [DPG] [Deterministic Policy Gradient Algorithms]](http://pic.xiahunao.cn/yaotu/[2014] [DPG] [Deterministic Policy Gradient Algorithms])
Deterministic Policy Gradient Algorithms, 2014随机策略：π θ ( a ∣ s ) = P [ a ∣ s ; θ ] π_\theta(a|s)=P[a|s;\theta]π
Deterministic Policy Gradient Algorithms, 2014随机策略：π θ ( a ∣ s ) = P [ a ∣ s ; θ ] π_\theta(a|s)=P[a|s;\theta]π
