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:
“I used to be a discipline problem, which caused me embarrassment until I realized that being a discipline problem in a racist society is sometimes an honor.”
—Ishmael Reed (b. 1938)
“Every child is an artist. The problem is how to remain an artist once he grows up.”
—Pablo Picasso (1881–1973)
“To make a good salad is to be a brilliant diplomatist—the problem is entirely the same in both cases. To know exactly how much oil one must put with one’s vinegar.”
—Oscar Wilde (1854–1900)