public abstract class GraphRF extends java.lang.Object implements RewardFunction
Domains. This class implements the standard
reward(burlap.oomdp.core.State, burlap.oomdp.singleagent.GroundedAction, burlap.oomdp.core.State)method by converting the
Stateobjects to their graph node integer representation and the
GroundedActionto its integer representation and then returning the value of
reward(int, int, int), which is an abstract method that the client must implement.
|Constructor and Description|
|Modifier and Type||Method and Description|
Returns the reward for taking action a in state node s and transition to state node sprime.
Returns the reward received when action a is executed in state s and the agent transitions to state sprime.
public double reward(State s, GroundedAction a, State sprime)
public abstract double reward(int s, int a, int sprime)
s- the previous state node id
a- the action id
sprime- the next state node id