Problem
The core problem of MDPs is to find a "policy" for the decision maker: a function that specifies the action that the decision maker will choose when in state . Note that once a Markov decision process is combined with a policy in this way, this fixes the action for each state and the resulting combination behaves like a Markov chain.
The goal is to choose a policy that will maximize some cumulative function of the random rewards, typically the expected discounted sum over a potentially infinite horizon:
- (where we choose )
where is the discount factor and satisfies . (For example, when the discount rate is r.) is typically close to 1.
Because of the Markov property, the optimal policy for this particular problem can indeed be written as a function of only, as assumed above.
Read more about this topic: Markov Decision Process
Famous quotes containing the word problem:
“Hypocrisy is the essence of snobbery, but all snobbery is about the problem of belonging.”
—Alexander Theroux (b. 1940)
“Every reform was once a private opinion, and when it shall be a private opinion again, it will solve the problem of the age.”
—Ralph Waldo Emerson (1803–1882)
“It is very comforting to believe that leaders who do terrible things are, in fact, mad. That way, all we have to do is make sure we don’t put psychotics in high places and we’ve got the problem solved.”
—Tom Wolfe (b. 1931)