Reinforcement Learning Toolbox

00001 // Copyright (C) 2003
00002 // Gerhard Neumann (gneumann@gmx.net)
00003 // Stephan Neumann (sneumann@gmx.net) 
00004 //                
00005 // This file is part of RL Toolbox.
00006 // http://www.igi.tugraz.at/ril_toolbox
00007 //
00008 // All rights reserved.
00009 // 
00010 // Redistribution and use in source and binary forms, with or without
00011 // modification, are permitted provided that the following conditions
00012 // are met:
00013 // 1. Redistributions of source code must retain the above copyright
00014 //    notice, this list of conditions and the following disclaimer.
00015 // 2. Redistributions in binary form must reproduce the above copyright
00016 //    notice, this list of conditions and the following disclaimer in the
00017 //    documentation and/or other materials provided with the distribution.
00018 // 3. The name of the author may not be used to endorse or promote products
00019 //    derived from this software without specific prior written permission.
00020 // 
00021 // THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
00022 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
00023 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
00024 // IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
00025 // INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
00026 // NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
00027 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
00028 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
00029 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
00030 // THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
00031 
00032 #ifndef CADVANTAGELEARNING_H
00033 #define CADVANTAGELEARNING_H
00034 
00035 #include "ctdlearner.h"
00036 
00037 class CAbstractVFunction;
00038 class CAbstractVETraces;
00039 
00040 #include "ril_debug.h"
00041 
00042 class CAdvantageUpdating : public CTDLearner
00043 {
00044 protected:
00045         //CVFunctionLearner *vFunctionLearner;
00046         CAbstractVFunction *vFunction;
00047         CAbstractVETraces *vETraces;
00048 
00049         virtual double getTemporalDifference(CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState);
00050 
00051         virtual void addETraces(CStateCollection *oldState, CStateCollection *newState, CAction *action);
00052         virtual void learnStep(CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState);
00053 public:
00054         //CAdvantageUpdating(CRewardFunction *rewardFunction, CAbstractQFunction *qfunction, CVFunctionLearner *vLearner, double dt);           
00055         CAdvantageUpdating(CRewardFunction *rewardFunction, CAbstractQFunction *qfunction, CAbstractVFunction *vFunction, double dt);           
00056         virtual ~CAdvantageUpdating();          
00057 
00058 };
00059 
00060 class CAdvantageLearner : public CTDResidualLearner
00061 {
00062 
00063 protected:
00064         CActionDataSet *actionDataSet2;
00065 
00066         virtual double getTemporalDifference(CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState);
00067 
00068         virtual void addETraces(CStateCollection *oldState, CStateCollection *newState, CAction *action, double td = 0.0);
00069 
00070 public:
00071 
00072         CAdvantageLearner(CRewardFunction *rewardFunction, CGradientQFunction *qfunction, double dt, CAbstractBetaCalculator *betaCalc);                
00073         ~CAdvantageLearner();
00074 };
00075 
00076 #endif
cadvantagelearning.h
