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_PRIORITZEDSWEEPING__H
00033 #define C_PRIORITZEDSWEEPING__H
00034 
00035 #include "cdynamicprogramming.h"
00036 #include "cbaseobjects.h"
00037 #include "cagentlistener.h"
00038 
00039 class CFeatureQFunction;
00040 class CStateModifier;
00041 class CAbstractFeatureStochasticModel;
00042 class CFeatureRewardFunction;
00043 class CFeatureVFunction;
00044 class CFeatureCalculator;
00045 
00046 
00047 #include <map>
00049 
00059 class CPrioritizedSweeping : public CSemiMDPListener, public CValueIteration, public CStateObject
00060 {
00061 protected:
00063         int kSteps;
00064                         
00065 public:
00066 
00071         CPrioritizedSweeping(CFeatureQFunction *qFunction, CStateModifier *discretizer, CAbstractFeatureStochasticModel *model, CFeatureRewardFunction *rewardFunction, int kSteps);
00072 
00073         CPrioritizedSweeping(CFeatureVFunction *vFunction, CStateModifier *discretizer, CAbstractFeatureStochasticModel *model, CFeatureRewardFunction *rewardFunction, int kSteps);
00074 
00075         virtual ~CPrioritizedSweeping();
00076 
00078 
00080         virtual void nextStep(CStateCollection *oldState, CAction *action, CStateCollection *newState);
00081 
00082         CFeatureCalculator *getFeatureCalculator();
00083 };
00084 
00085 #endif
00086
cprioritizedsweeping.h
