csupervisedlearner.h

强化学习算法（R-Learning）难得的珍贵资料

// Copyright (C) 2003
// Gerhard Neumann ([e-mail])

//                
// This file is part of RL Toolbox.
// http://www.igi.tugraz.at/ril_toolbox
//
// All rights reserved.
// 
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
// 1. Redistributions of source code must retain the above copyright
//    notice, this list of conditions and the following disclaimer.
// 2. Redistributions in binary form must reproduce the above copyright
//    notice, this list of conditions and the following disclaimer in the
//    documentation and/or other materials provided with the distribution.
// 3. The name of the author may not be used to endorse or promote products
//    derived from this software without specific prior written permission.
// 
// THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
// IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
// OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
// IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
// INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
// NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
// THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#ifndef c_SUPERVISEDTRAINER__H
#define c_SUPERVISEDTRAINER__H

#include "cutility.h"
#include "cparameters.h"
#include "cgradientfunction.h"
#include "clearndataobject.h"
#include "ril_debug.h"

class CSupervisedLearner : public CLearnDataObject
{
protected:
	CMyVector *outputError;

public:
	CSupervisedLearner(int nInputs, int nOutputs);
	~CSupervisedLearner();

	virtual void learnExample(CMyVector *input, CMyVector *target);
	virtual void testExample(CMyVector *input, CMyVector *output) = 0;
	virtual void learnExample(CMyVector *input, CMyVector *target, CMyVector *outputError) = 0;

	virtual int getNumInputs() = 0;
	virtual int getNumOutputs() = 0;
};

class CSupervisedGradientFunctionLearner : public CSupervisedLearner
{
protected:
	CGradientFunction *gradientFunction;

	CFeatureList *gradient;
	CFeatureList *localGradient;

public:
	CSupervisedGradientFunctionLearner(CGradientFunction *gradientFunction);
	~CSupervisedGradientFunctionLearner();

	virtual void learnExample(CMyVector *input, CMyVector *target, CMyVector *outputError);
	virtual void testExample(CMyVector *input, CMyVector *output);

	virtual int getNumInputs();
	virtual int getNumOutputs();

	virtual void saveData(FILE *stream);

	virtual void loadData(FILE *stream);	

	virtual void resetData();
};

#endif