domain sysadmin_mdp {
requirements = {
reward-deterministic
};
types {
computer : object;
};
pvariables {
reboot(computer) : {action-fluent, bool, default = false};
CONNECTED(computer, computer) : {non-fluent, bool, default = false};
REBOOT-PENALTY : {non-fluent, real, default = 0.75};
REBOOT-PROB : {non-fluent, real, default = 0.1};
running(computer) : {state-fluent, bool, default = false};
};
cpfs {
(running’ ?x) = (if (reboot ?x) then (KronDelta true) else (if (running ?x) then (Bernoulli (+ 0.45 (/ (* 0.5 (+ 1 (sum ( (?y : computer) ) (^ (CONNECTED ?y ?x) (running ?y) )))) (+ 1 (sum ( (?y : computer) ) (CONNECTED ?y ?x)))))) else (Bernoulli (REBOOT-PROB))));
};
reward = (sum ( (?c : computer) ) (- (running ?c) (* (REBOOT-PENALTY) (reboot ?c))));
state-action-constraints {
};
}