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 CAGENTCONTROLLER_H
00033 #define CAGENTCONTROLLER_H
00034 
00035 #include "cbaseobjects.h"
00036 #include "cagentlistener.h"
00037 #include "cparameters.h"
00038 
00039 
00040 #include <list>
00041 
00042 class CStateCollection;
00043 class CActionStatistics;
00044 
00046 
00052 class CAgentController : public CActionObject, virtual public CParameterObject
00053 {
00054 public:
00056         CAgentController(CActionSet *actions);
00057         virtual ~CAgentController();
00058 
00060         virtual CAction* getNextAction(CStateCollection *state, CActionDataSet *data = NULL) = 0;
00061         
00062 };
00063 
00065 
00070 class CAgentStatisticController : public CAgentController
00071 {
00072 public:
00073         CAgentStatisticController(CActionSet *actions);
00074 
00075         virtual CAction* getNextAction(CStateCollection *state, CActionDataSet *data = NULL);
00076         virtual CAction* getNextAction(CStateCollection *, CActionDataSet * = NULL, CActionStatistics * = NULL) {return NULL;};
00077 };
00078 
00080 
00094 class CDeterministicController : public CAgentController, public CSemiMDPListener
00095 {
00096 protected:
00098         CAction *nextAction;
00100 
00103         CAgentController *controller;
00105 
00108         CAgentStatisticController *statisticController;
00110         CActionStatistics *statistics;
00111         bool useStatisticController;
00112 
00114         CActionDataSet *actionDataSet;
00115 
00116         void initStatistics();
00117 
00118 public:
00120         CDeterministicController(CActionSet *actions);
00122         CDeterministicController(CAgentController *controller);
00124         CDeterministicController(CAgentStatisticController *controller);
00125         virtual ~CDeterministicController();
00126 
00128 
00130         virtual CAction* getNextAction(CStateCollection *state, CActionDataSet *data = NULL);
00131 
00133         virtual void nextStep(CStateCollection *state1, CAction *action, CStateCollection *state2);
00135         virtual void newEpisode();
00136     
00138 
00139         CActionStatistics *getLastActionStatistics();
00140     bool isUsingStatisticController();
00141         
00143         void setController(CAgentController *controller);
00145 
00146         void setController(CAgentStatisticController *controller);
00147 
00148         CAgentController *getController() {return controller;};
00149 
00150         void setNextAction(CAction *action, CActionData *data = NULL);
00151 };
00152 
00153 
00154 #endif
cagentcontroller.h
