0 # initial state
[4] # terminal state
(0,1,'c&!d',ConstantRewardFunction(1))
(0,2,'d',ConstantRewardFunction(0))
(0,0,'!c&!d',ConstantRewardFunction(0))
(1,4,'t&!d',ConstantRewardFunction(1))
(1,3,'d',ConstantRewardFunction(0))
(1,1,'!t&!d',ConstantRewardFunction(0))
(2,3,'c',ConstantRewardFunction(1))
(2,2,'!c',ConstantRewardFunction(0))
(3,4,'t',ConstantRewardFunction(-1))
(3,3,'!t',ConstantRewardFunction(0))
