net.sourceforge.cilib.games.agent.neural
Class NeuralOutputInterpretationStrategy

java.lang.Object
  net.sourceforge.cilib.games.agent.neural.NeuralOutputInterpretationStrategy

Direct Known Subclasses:

NeuralPredatorOutputStrategy, NeuralPreyOutputStrategy

public abstract class NeuralOutputInterpretationStrategy
extends Object

Author:

leo This class is used by the NeuralAgent to alter the given game state by the output vector of the Neural Network after the input has been processed.

Constructor Summary

NeuralOutputInterpretationStrategy()

Method Summary

abstract void	applyOutputToState(TypeList outputData, Agent currentPlayer, Game<GameState> oldState) Modify the game by the output vector
abstract int	getAmOutputs() the the number of output units that this strategy requires

Methods inherited from class java.lang.Object

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

Constructor Detail

NeuralOutputInterpretationStrategy

public NeuralOutputInterpretationStrategy()

Method Detail

getAmOutputs

public abstract int getAmOutputs()

the the number of output units that this strategy requires

Returns:

the output count

applyOutputToState

public abstract void applyOutputToState(TypeList outputData,
                                        Agent currentPlayer,
                                        Game<GameState> oldState)

Modify the game by the output vector

Parameters:

outputData - the output data vector

currentPlayer - the agent that is represented by the Neural Network

oldState - the game state to be altered