Skip to main content
1 of 4
DSPinfinity
  • 1.1k
  • 3
  • 10

Unclear equation for optimality of the greedy policy

I did not understand how the equation below is obtained:

enter image description here

where $\pi^{\prime}(x_k)=argmax_{u_k \in \mathcal{U}}q_{\pi}(x_k, u_k)$.

Note: the source of the above equation is slide 22, at the follwing link: https://groups.uni-paderborn.de/lea/share/lehre/reinforcementlearning/lecture_slides/built/Lecture03.pdf

DSPinfinity
  • 1.1k
  • 3
  • 10