hdjsjshshsh
hdjsjshshsh
12.03.2020 • 
Mathematics

For each of the following action-selection methods, indicate which option describes it best. A: With probability pp, select argmax_a Q(s,a)argmax a Q(s,a). With probability 1-p1−p, select a random action. p=0.99p=0.99

Solved
Show answers

Ask an AI advisor a question