org.vizzini.example.tictactoe
Class NeuralNetworkEvaluator

java.lang.Object
  extended by org.vizzini.game.AbstractEvaluator
      extended by org.vizzini.game.AbstractNeuralNetworkEvaluator
          extended by org.vizzini.game.boardgame.AbstractNeuralGridBoardEvaluator
              extended by org.vizzini.example.tictactoe.NeuralNetworkEvaluator
All Implemented Interfaces:
Serializable, IEvaluator

public class NeuralNetworkEvaluator
extends AbstractNeuralGridBoardEvaluator

Provides a neural network evaluator for tic-tac-toe.

Since:
v0.1
Version:
v0.2
Author:
Jeffrey M. Thompson
See Also:
Serialized Form

Constructor Summary
NeuralNetworkEvaluator()
           
 
Method Summary
protected  double[] encode(IGridBoard gridBoard, IAgent agent)
          Encode the given grid board as appropriate for a neural network input.
 
Methods inherited from class org.vizzini.game.boardgame.AbstractNeuralGridBoardEvaluator
arrayToString, evaluateTokens
 
Methods inherited from class org.vizzini.game.AbstractNeuralNetworkEvaluator
configure, getNeuralNetwork, setNeuralNetwork
 
Methods inherited from class org.vizzini.game.AbstractEvaluator
evaluate, multiplier
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

NeuralNetworkEvaluator

public NeuralNetworkEvaluator()
Method Detail

encode

protected double[] encode(IGridBoard gridBoard,
                          IAgent agent)
Encode the given grid board as appropriate for a neural network input.

The tic-tac-toe board has nine positions. Each position contains an empty, X, or O. The neural network therefore has 18 inputs, 2 for each position.

Specified by:
encode in class AbstractNeuralGridBoardEvaluator
Since:
v0.1


Copyright 2007 Vizzini.org. All Rights Reserved. 2007.12.25.03.00.02