- Type Parameters:
S
- the state type.
A
- the action type.
- All Known Implementing Classes:
- LookupPolicy
public interface Policy<S,A extends Action>
Artificial Intelligence A Modern Approach (3rd Edition): page 647.
A solution to a Markov decision process is called a policy. It
specifies what the agent should do for any state that the agent might reach.
It is traditional to denote a policy by π, and π(s) is the action
recommended by the policy π for state s. If the agent has a complete
policy, then no matter what the outcome of any action, the agent will always
know what to do next.
- Author:
- Ciaran O'Reilly, Ravi Mohan