Machine-translated by Google. Questions are authored in English.
Top

Discussion

Why does a Markov decision process require a policy rather than a plan?

  • A.The outcome of an action determines what should be done next
  • B.The goal changes as the process evolves over time
  • C.The state space is too large to compute a sequence for
  • D.Policies are always shorter to represent than plans

Answer: A

Since an action may lead to any of several states, the agent cannot know in advance which it will occupy and must be prepared with an action for each. A fixed sequence would be wrong as soon as an unexpected outcome occurred. Goals are fixed, size is a separate issue and policies are usually larger. Uncertainty in outcomes converting a sequence into a mapping is the same distinction that separates plans from policies generally.

No comment is present. Be the first to comment.
Loading…

Post your comment

Please log in or register to post a comment.