Reinforcement Learning Toolbox 2.0 last updated:

General Documentation Manual Tutorial Class Reference Master Thesis Examples Related Papers Downloads Links News mailto:webmaster Main Page     Class Hierarchy   Compound List   File List   Compound Members   File Members cagentlogger.h Go to the documentation of this file. // Copyright (C) 2003 // Gerhard Neumann (gneumann@gmx.net) // Stephan Neumann (sneumann@gmx.net) // // This file is part of RL Toolbox. // http://www.igi.tugraz.at/ril_toolbox // // All rights reserved. // // Redistribution and use in source and binary forms, with or without // modification, are permitted provided that the following conditions // are met: // 1. Redistributions of source code must retain the above copyright // notice, this list of conditions and the following disclaimer. // 2. Redistributions in binary form must reproduce the above copyright // notice, this list of conditions and the following disclaimer in the // documentation and/or other materials provided with the distribution. // 3. The name of the author may not be used to endorse or promote products // derived from this software without specific prior written permission. // // THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. // IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, // INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT // NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF // THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #ifndef CAGENTLOGGER_H #define CAGENTLOGGER_H #include "cagentlistener.h" #include "cepisodehistory.h" #include "cbaseobjects.h" #include <stdio.h> #include <list> class CEpisode; class CStateModifier; class CAgentLogger: public CSemiMDPListener, public CEpisodeHistory { protected: char filename[512]; FILE* file; char loadFileName[512]; std::list<CStateModifier *> *loadModifiers; int holdMemory; std::list<CEpisode *> *episodes; CEpisode *currentEpisode; void init(); public: CAgentLogger(CStateProperties *model, CActionSet *actions, char* autoSavefile, int holdMemory); CAgentLogger(CStateProperties *model, CActionSet *actions); CAgentLogger(char *loadFile, CStateProperties *model, CActionSet *actions, std::list<CStateModifier *> *modifiers); virtual ~CAgentLogger(); virtual void nextStep(CStateCollection *oldState, CAction *action, CStateCollection *nextState); virtual void newEpisode(); void setAutoSaveFile(char *filename); virtual void saveBIN(FILE *stream); virtual void saveData(FILE *stream); void loadBIN(FILE *stream, std::list<CStateModifier *> *modifiers, int episodes = -1); virtual void loadData(FILE *stream, int episodes = -1); virtual void loadData(FILE *stream); virtual int getNumEpisodes(); virtual void addStateModifier(CStateModifier *modifier); virtual void removeStateModifier(CStateModifier *modifier); virtual CEpisode* getCurrentEpisode(); virtual CEpisode* getEpisode(int index); void clearAutoSaveFile(); void setLoadDataFile(char *loadData, std::list<CStateModifier *> *modifiers = NULL); virtual void resetData(); }; class CEpisodeOutput : public CSemiMDPRewardListener, public CActionObject, public CStateObject { protected: FILE *stream; int nEpisodes; int nSteps; public: CEpisodeOutput(CStateProperties *featCalc, CRewardFunction *rewardFunction, CActionSet *actions, FILE *output); virtual ~CEpisodeOutput(); virtual void nextStep(CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState); virtual void intermediateStep(CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState); virtual void newEpisode(); }; class CEpisodeMatlabOutput : public CSemiMDPRewardListener, public CActionObject, public CStateObject { protected: FILE *stream; int nSteps; public: int nEpisodes; CEpisodeMatlabOutput(CStateProperties *featCalc, CRewardFunction *rewardFunction, CActionSet *actions, FILE *output); virtual ~CEpisodeMatlabOutput(); virtual void nextStep(CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState); virtual void newEpisode(); void setOutputFile(FILE *stream); }; class CEpisodeOutputStateChanged : public CEpisodeOutput { public: CEpisodeOutputStateChanged(CStateProperties *featCalc, CRewardFunction *rewardFunction, CActionSet *actions, FILE *output); virtual ~CEpisodeOutputStateChanged() {}; virtual void nextStep(CStateCollection *oldState, CAction *action, double reward, CStateCollection *nextState); }; class CStateOutput : public CSemiMDPListener, public CStateObject { protected: FILE *stream; public: CStateOutput(CStateProperties *featCalc, FILE *output); virtual ~CStateOutput(); virtual void nextStep(CStateCollection *oldState, CAction *action, CStateCollection *nextState); }; class CActionOutput : public CSemiMDPListener, public CActionObject { protected: FILE *stream; public: CActionOutput(CActionSet *actions, FILE *output); virtual ~CActionOutput(); virtual void nextStep(CStateCollection *oldState, CAction *action, CStateCollection *nextState); }; #endif