csupervisedlearner.cpp

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.
#include "csupervisedlearner.h"

CSupervisedLearner::CSupervisedLearner(int nInputs, int nOutputs)
{
	outputError = new CMyVector(nOutputs);
}


CSupervisedLearner::~CSupervisedLearner()
{
	delete outputError;
}


void CSupervisedLearner::learnExample(CMyVector *input, CMyVector *target)
{
	testExample(input, outputError);
	outputError->multScalar(-1.0);
	outputError->addVector(target);

	learnExample(input, target, outputError);
}

CSupervisedGradientFunctionLearner::CSupervisedGradientFunctionLearner(CGradientFunction *gradientFunction) : CSupervisedLearner(gradientFunction->getNumInputs(), gradientFunction->getNumOutputs())
{
	this->gradientFunction = gradientFunction;
	this->gradient = new CFeatureList();
	this->localGradient = new CFeatureList();

	addParameter("SGLLearningRate", 0.01);
	addParameter("SGMLMomentum",0.1);

	addParameters(gradientFunction);
}

CSupervisedGradientFunctionLearner::~CSupervisedGradientFunctionLearner()
{
	delete gradient;
}

void CSupervisedGradientFunctionLearner::learnExample(CMyVector *input, CMyVector *target, CMyVector *outputError)
{
	localGradient->clear();
	gradient->multFactor(getParameter("SGMLMomentum"));

	gradientFunction->getGradient(input, outputError, localGradient);
	gradient->add(localGradient);

	gradientFunction->updateGradient(gradient, getParameter("SGLLearningRate"));
}



void CSupervisedGradientFunctionLearner::testExample(CMyVector *input, CMyVector *output)
{
	gradientFunction->getFunctionValue(input, output);
}

int CSupervisedGradientFunctionLearner::getNumInputs()
{
	return gradientFunction->getNumInputs();
}

int CSupervisedGradientFunctionLearner::getNumOutputs()
{
	return gradientFunction->getNumOutputs();
}

void CSupervisedGradientFunctionLearner::saveData(FILE *stream)
{
	gradientFunction->saveData(stream);
}

void CSupervisedGradientFunctionLearner::loadData(FILE *stream)
{
	gradientFunction->loadData(stream);
}

void CSupervisedGradientFunctionLearner::resetData()
{
	gradientFunction->resetData();
}