# Stochastic version of Michael's 1D maze

discount: 0.75
values: reward
states: left middle right goal
actions: w0 e0 
observations: nothing goal

start: 
0.333333 0.333333 0.333333 0.0

T: w0
0.9 0.1 0.0 0.0 
0.9 0.0 0.0 0.1 
0.0 0.0 0.1 0.9 
0.333333 0.333333 0.333333 0.0

T: e0
0.1 0.9 0.0 0.0 
0.1 0.0 0.0 0.9 
0.0 0.0 0.9 0.1 
0.333333 0.333333 0.333333 0.0

O: * 
1.0 0.0 
1.0 0.0 
1.0 0.0 
0.0 1.0 

R: * : * : goal : goal 1.0