All Implemented Interfaces:
Direct Known Subclasses:
public abstract class
This abstract class is used to define shaped reward functions. Shaped reward functions take the base
true objective reward function of a task and add some additional reward value to it that helps suggest
useful states. Subclasses of the ShapedRewardFunction must implement a method that specifies the
additive reward to the base reward.
Author: James MacGlashan
Modifier and Type
Field and Description
The base objective reward function for the task.
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
public abstract double additiveReward(
Returns the reward value to add to the base objective reward function.
s - the previous state
a - the action taken the previous state
sprime - the successor state
Returns: the reward value to add to the base objective reward function.
public double reward(
Returns the reward received when action a is executed in state s and the agent transitions to state sprime.
s - the state in which the action was executed
a - the action executed
sprime - the state to which the agent transitioned
Returns: the reward received when action a is executed in state s and the agent transitions to state sprime.