let aStayStrategy = (door,choice) =>
switch(door,choice){ | (DoorA,Stay) => 1.0 | _ => 0.0 };
expected_reward(
make_scenario_pmf(pDoorsBiased,aStayStrategy)
);
let cSwapStrategy = (door,choice) =>
switch(door,choice){ | (DoorC,Swap) => 1.0 | _ => 0.0 };
expected_reward(
make_scenario_pmf(pDoorsBiased,cSwapStrategy)
);
val aStayStrategy : door -> choice -> Q.t = <fun>
- : real = 600000
val cSwapStrategy : door -> choice -> Q.t = <fun>
- : real = 800000