# It is a line of uniquely appearing states with a goal at both ends.

discount: 1.0
values: reward
states: 4
actions: left right
observations: nothing

T: left
1.0 0.0 0.0 0.0
0.8 0.1 0.1 0.0
0.0 0.8 0.1 0.1
0.0 0.0 0.0 1.0

T: right
1.0 0.0 0.0 0.0
0.1 0.1 0.8 0.0
0.0 0.1 0.1 0.8
0.0 0.0 0.0 1.0

O: * : * : * 1.0

R: left : 1 : 0 : * 1.0
R: right : 2 : 3 : * 1.0