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_EPISODE_H
00033 #define C_EPISODE_H
00034 
00035 #include <vector>
00036 #include <vector>
00037 #include <map>
00038 
00039 #include "chistory.h"
00040 #include "cagentlistener.h"
00041 
00042 class CState;
00043 class CStateProperties;
00044 class CStateCollection;
00045 class CStateCollectionList;
00046 class CStateModifier;
00047 class CStateList;
00048 class CAction;
00049 class CActionList;
00050 class CActionDataSet;
00051 
00053 
00061 class CEpisode : public CSemiMDPListener, public CStepHistory
00062 {
00063 protected:
00064 
00066         bool autoNewEpisode;
00067 
00069         CStateCollectionList *stateCollectionList;
00071         CActionList *actionList;
00072 public:
00074         CEpisode(CStateProperties *properties, CActionSet *actions, bool autoNewEpisode = true);
00076 
00077         CEpisode(CStateProperties *properties, CActionSet *actions, std::list<CStateModifier *> *modifiers, bool autoNewEpisode = true);
00078         virtual ~CEpisode();
00079 
00082         virtual void nextStep(CStateCollection *oldState, CAction *action, CStateCollection *newState );
00083 
00085         virtual void newEpisode();
00086 
00087         CStateList *getStateList(CStateProperties *properties);
00088 
00090         void getStateCollection(int index, CStateCollectionImpl *stateCollection);
00092         void getState(int index, CState *state);
00093 
00095         virtual void addStateModifier(CStateModifier *modifier);
00097         virtual void removeStateModifier(CStateModifier *modifier);
00098 
00100         CAction *getAction(unsigned int num, CActionDataSet *dataSet = NULL);
00101 
00103 
00104         void saveBIN(FILE *stream);
00106 
00107         void loadBIN(FILE *stream);
00108 
00110 
00111         virtual void saveData(FILE *stream);
00113 
00114         virtual void loadData(FILE *stream);
00115 
00117         virtual int getNumSteps();
00118 
00120         virtual void getStep(int num, CStep *step);
00121 
00122         virtual int getNumStateCollections();
00123 
00124         virtual void resetData();
00125 };
00126 
00127 
00128 
00129 
00130 #endif
00131 
00132
cepisode.h
