org.eyelanguage.rl.reading
Class ReadingParallelReinforcementFunction

java.lang.Object
  net.pakl.rl.ReinforcementFunction
      org.eyelanguage.rl.reading.ReadingReinforcementFunction
          org.eyelanguage.rl.reading.ReadingParallelReinforcementFunction

public class ReadingParallelReinforcementFunction
extends ReadingReinforcementFunction

Constructor Summary

ReadingParallelReinforcementFunction(SentenceWorld sWorld)

Method Summary

double	getReward(State state, Action action) Return the reward given an action from a particular state.
double	getReward(State state, Action action, State resultingState) Sometimes a reward is also based on the resulting state.
double	getRewardForSuccessfulIdentification()
void	setReinforcementsForActionsOntoTerminalState(double reward)
void	setRewardForSuccessfulIdentification(double rewardForSuccessfulIdentification)

Methods inherited from class net.pakl.rl.ReinforcementFunction

getDefaultReinforcement, setDefaultReinforcement, setReward, toText

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ReadingParallelReinforcementFunction

public ReadingParallelReinforcementFunction(SentenceWorld sWorld)

Method Detail

setReinforcementsForActionsOntoTerminalState

public void setReinforcementsForActionsOntoTerminalState(double reward)

Overrides:

setReinforcementsForActionsOntoTerminalState in class ReadingReinforcementFunction

getReward

public double getReward(State state,
                        Action action)

Description copied from class: ReinforcementFunction

Return the reward given an action from a particular state.

Overrides:

getReward in class ReadingReinforcementFunction

getReward

public double getReward(State state,
                        Action action,
                        State resultingState)

Description copied from class: ReinforcementFunction

Sometimes a reward is also based on the resulting state. Rather than re-computing the resulting state of the action (and if the results of actions are stochastic rather than deterministic, that could be the wrong thing to do), this function lets you pass in the state that actually resulted.

Overrides:

getReward in class ReadingReinforcementFunction

getRewardForSuccessfulIdentification

public double getRewardForSuccessfulIdentification()

Overrides:

getRewardForSuccessfulIdentification in class ReadingReinforcementFunction

setRewardForSuccessfulIdentification

public void setRewardForSuccessfulIdentification(double rewardForSuccessfulIdentification)

Overrides:

setRewardForSuccessfulIdentification in class ReadingReinforcementFunction