creinforce.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_REINFORCE__H
#define C_REINFORCE__H

#include "cagentlistener.h"
#include "crewardfunction.h"
#include "cpolicies.h"
#include "cgradientfunction.h"
#include "ril_debug.h"

class CReinforcementBaseLineCalculator : virtual public CParameterObject
{
public:
	virtual rlt_real getReinforcementBaseLine(int feature) = 0;
};

class CConstantReinforcementBaseLineCalculator : public CReinforcementBaseLineCalculator
{
public:
	CConstantReinforcementBaseLineCalculator(rlt_real b);

	virtual rlt_real getReinforcementBaseLine(int feature);
};

class CAverageReinforcementBaseLineCalculator : public CReinforcementBaseLineCalculator, public CSemiMDPRewardListener 
{
protected:
	rlt_real averageReward;
	int steps;
public:
	CAverageReinforcementBaseLineCalculator(CRewardFunction *reward, rlt_real minUpdateFactor);

	virtual rlt_real getReinforcementBaseLine(int feature);

	virtual void nextStep(CStateCollection *oldState, CAction *action, rlt_real reward, CStateCollection *nextState);
	virtual void newEpisode();
};

class CREINFORCELearner : public CSemiMDPRewardListener
{
protected:
	CStochasticPolicy *policy;
	CGradientUpdateFunction *updateFunction;

	CReinforcementBaseLineCalculator *baseLine;

	CFeatureList *gradient;
	CGradientVETraces *eTraces;
public:
	CREINFORCELearner(CRewardFunction *reward, CStochasticPolicy *policy, CGradientUpdateFunction *updateFunction, CReinforcementBaseLineCalculator *baesLine);
	~CREINFORCELearner();

	virtual void nextStep(CStateCollection *oldState, CAction *action, rlt_real reward, CStateCollection *nextState);	
	virtual void newEpisode();

	CGradientVETraces *getETraces();

};

#endif