diaporamaMiscDM
 
◃  Ch. 6 App par renforcement  ▹
 

Calculs de Q(s,a) (2/2)

  • Q(6,N)= 0 + β (+1 + γ * -0.2 -0) = 0.184
  • Q(6,O)= 0 + β (-1 + γ * 0.2 - 0) = -0.184
  • Q(6,S)= 0 + β (-1 + γ * 0.2 - 0) = -0.184
  • Q(9,N)= 0 + β (1 + γ * 0.2 - 0) = 0.216
  • Q(9,E)= 0 + β (1 + γ * 0.2 - 0) = 0.216
  • Q(9,O)= 0 + β (-1 + γ * 0 - 0) = -0.2
  • Q(8,O)= 0 + β (-1 + γ * 0.2 - 0) = -0.184
  • Q(8,E)= 0 + β (1 + γ * 0.216 - 0) = 0.21728