Author Question: Which is not a method to determine an optimal stationary policy? a.value iteration b.IP c.LP ... (Read 68 times)

moongchi

  • Hero Member
  • *****
  • Posts: 516
Which is not a method to determine an optimal stationary policy?
  a.value iteration
  b.IP
  c.LP
  d.policy iteration

Question 2

In an MDP the next period's state depends on
  a.all previous states and only the current decision chosen.
  b.only the current period's state and the current decision chosen.
  c.all previous states and all previous decisions.
  d.only the current period's state and all previous decisions chosen.



kjohnson

  • Sr. Member
  • ****
  • Posts: 330
Answer to Question 1

correct: b

Answer to Question 2

correct: b



Related Topics

Need homework help now?

Ask unlimited questions for free

Ask a Question
 

Did you know?

Automated pill dispensing systems have alarms to alert patients when the correct dosing time has arrived. Most systems work with many varieties of medications, so patients who are taking a variety of drugs can still be in control of their dose regimen.

Did you know?

Only 12 hours after an egg cell is fertilized by a sperm cell, the egg cell starts to divide. As it continues to divide, it moves along the fallopian tube toward the uterus at about 1 inch per day.

Did you know?

Chronic marijuana use can damage the white blood cells and reduce the immune system's ability to respond to disease by as much as 40%. Without a strong immune system, the body is vulnerable to all kinds of degenerative and infectious diseases.

Did you know?

The horizontal fraction bar was introduced by the Arabs.

Did you know?

Amphetamine poisoning can cause intravascular coagulation, circulatory collapse, rhabdomyolysis, ischemic colitis, acute psychosis, hyperthermia, respiratory distress syndrome, and pericarditis.

For a complete list of videos, visit our video library