[Size] rows = 3 cols = 4 [Transition model] "((*,*), FORWARD)" = 0.8 "((*,*), LEFT)" = 0.1 "((*,*), RIGHT)" = 0.1 #"(1 , 1), UP, (2, 1)" = 0.8 [Rewards] (*,*) = -0.04 #(*,*) = -0.01 (3,4) = 1 (2,4) = -1 [Holes] 1 = (2,2) [Discount factor] gamma =1 [Terminate states] 1 = (3,4) 2 = (2,4)