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 C_FUNCTIONFROMQFUNCTION__H
00033 #define C_FUNCTIONFROMQFUNCTION__H
00034 
00035 #include "cvfunction.h"
00036 
00037 class CAbstractQFunction;
00038 class CActionSet;
00039 class CStateProperties;
00040 class CStateCollection;
00041 class CState;
00042 class CAbstractVETraces;
00043 
00044 class COptimalVFunctionFromQFunction : public CAbstractVFunction 
00045 {
00046 protected:
00047         CAbstractQFunction *qFunction;
00048         CActionSet *availableActions;
00049 public:
00050         COptimalVFunctionFromQFunction(CAbstractQFunction *qfunction, CStateProperties *properties);
00051         virtual ~COptimalVFunctionFromQFunction();
00052 
00053         virtual double getValue(CStateCollection *state);
00054         virtual double getValue(CState *state);
00055 
00056         virtual CAbstractVETraces *getStandardETraces();
00057 };
00058 
00059 class CVFunctionFromQFunction : public COptimalVFunctionFromQFunction
00060 {
00061 protected:
00062         
00063         double *actionValues;
00064         CStochasticPolicy *stochPolicy;
00065 
00066 public:
00067         CVFunctionFromQFunction(CAbstractQFunction *qfunction, CStochasticPolicy *stochPolicy, CStateProperties *properties);
00068         virtual ~CVFunctionFromQFunction();
00069 
00070         virtual double getValue(CStateCollection *state);
00071         virtual double getValue(CState *state);
00072 
00073         virtual CStochasticPolicy *getPolicy();
00074         virtual void setPolicy( CStochasticPolicy *policy);
00075 };
00076 
00077 #endif
00078
cvfunctionfromqfunction.h
