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 CMULTIPOLEMODEL_H
00033 #define CMULTIPOLEMODEL_H
00034 
00035 #include "cenvironmentmodel.h"
00036 #include "crewardfunction.h"
00037 #include "cagentcontroller.h"
00038 #include "cdiscretizer.h"
00039 #include "caction.h"
00040 
00041 #include <math.h>
00042 
00043 class CMultiPoleDiscreteState : public CAbstractStateDiscretizer
00044 {
00045 public:
00046                 CMultiPoleDiscreteState();
00047                 virtual ~CMultiPoleDiscreteState() {};
00048 
00049                 virtual unsigned int getDiscreteStateNumber(CStateCollection *state);           
00050 };
00051 
00052 class CMultiPoleFailedState : public CAbstractStateDiscretizer
00053 {
00054 public: 
00055         CMultiPoleFailedState();
00056         virtual ~CMultiPoleFailedState() {};
00057 
00058         virtual unsigned int getDiscreteStateNumber(CStateCollection *state);           
00059 };
00060 
00061 class CMultiPoleModel : public CEnvironmentModel, public CRewardFunction
00062 {
00063 protected:
00065         double x, x_dot, theta, theta_dot; 
00067         virtual void doNextState(CPrimitiveAction *action); 
00068 
00069 public:
00070         CMultiPoleModel();
00071         virtual ~CMultiPoleModel();
00072         
00074         virtual double getReward(CStateCollection *oldState, CAction *action, CStateCollection *newState); 
00076         virtual void getState(CState *state);
00078         virtual void doResetModel();
00079 };
00080 
00081 class CMultiPoleContinuousReward : public CStateReward
00082 {
00083 public:
00084         CMultiPoleContinuousReward(CStateProperties *modelState);
00085         virtual ~CMultiPoleContinuousReward() {};
00086 
00087         double getStateReward(CState *modelState);
00088 };
00089 
00090 
00091 class CMultiPoleAction : public CPrimitiveAction
00092 {
00093 protected:
00094         double force;
00095 
00096 public:
00097         CMultiPoleAction(double force);
00098 
00099         double getForce();
00100 };
00101 
00102 
00103 class CMultiPoleController : public CAgentController
00104 {
00105 protected:
00106 
00107 public:
00108         CMultiPoleController(CActionSet *actions);
00109         virtual ~CMultiPoleController();
00110 
00111         virtual CAction* getNextAction(CStateCollection *state, CActionDataSet *data = NULL);
00112 };
00113 
00114 class CMultiPoleDiscreteController : public CAgentController, CStateObject
00115 {
00116 protected:
00117 
00118 public:
00119         CMultiPoleDiscreteController(CActionSet *actions, CStateProperties *discState);
00120         virtual ~CMultiPoleDiscreteController();
00121 
00122         virtual CAction* getNextAction(CStateCollection *state, CActionDataSet *data = NULL);
00123 };
00124 
00125 
00126 #endif
00127 
00128
cmultipolemodel.h
