mdp

module main
	s : [0..6] init 6;

	[] s=6 -> 1 : (s'=0);
	[] s=6 -> 1 : (s'=5);
	[a] s=5 -> 1 : (s'=5);
	[b] s=5 -> 1 : (s'=1); 
	[] s=0 -> 1/10: (s'=1) + 9/10: (s'=3);
	[] s=0 -> 1/10: (s'=1) + 9/10: (s'=4);
	[a] s=3 -> 1: (s'=0);
	[b] s=3 -> 1: (s'=0);
	[]  s=1 -> 1: (s'=2);
	[] s=2 -> 1: (s'=2);
endmodule
 
rewards "first"
	[a] true : 1;
endrewards
 
rewards "second"
	[b] s=3 : 1;
	[b] s=5 : 2;
endrewards

rewards "third"
	true : 0.7;
endrewards