You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
33 lines
563 B
33 lines
563 B
// Modified running example MDP (see Example 7, p.17)
|
|
|
|
mdp
|
|
|
|
module M
|
|
|
|
// s=i for state s_i
|
|
s : [0..3]; //
|
|
|
|
[wait] s=0 -> (s'=0);
|
|
[go] s=0 -> (s'=1);
|
|
[safe] s=1 -> 0.7:(s'=0) + 0.3:(s'=2);
|
|
[risk] s=1 -> 0.5:(s'=2) + 0.5:(s'=3);
|
|
[finish] s=2 -> (s'=2);
|
|
[stop] s=3 -> (s'=3);
|
|
[reset] s=3 -> (s'=0);
|
|
|
|
endmodule
|
|
|
|
rewards
|
|
// state rewards
|
|
s=0 : 1;
|
|
s=1 : 2;
|
|
// transition rewards
|
|
[go] s=0 : 1;
|
|
[safe] s=1 : 1;
|
|
[risk] s=1 : 4;
|
|
[reset] s=3 : 5;
|
|
endrewards
|
|
|
|
label "initial" = s=0;
|
|
label "succ" = s=2;
|
|
label "fail" = s=3;
|