Warrior_EA/references/MQL5/Experts/CFPI/Study.mq5

<EFBFBD><EFBFBD>//+------------------------------------------------------------------+

//|                                                        Study.mq5 |

//|                                                   Copyright DNG<EFBFBD> |

//|                                https://www.mql5.com/en/users/dng |

//+------------------------------------------------------------------+

#property copyright "Copyright DNG<00>"

#property link      "https://www.mql5.com/en/users/dng"

#property version   "1.00"

//+------------------------------------------------------------------+

//|                                                                  |

//+------------------------------------------------------------------+

#define Study

#include "Trajectory.mqh"

//+------------------------------------------------------------------+

//| Input parameters                                                 |

//+------------------------------------------------------------------+

input int                  Iterations     = 10000;

input int                  BatchSize      = 256;

//+------------------------------------------------------------------+

//|                                                                  |

//+------------------------------------------------------------------+

STrajectory          Buffer[];

CNet                 Actor;

CNet                 Critic1;

CNet                 Critic2;

CNet                 StateEncoder;

//---

float                dError;

datetime             dtStudied;

//---

CBufferFloat         State;

CBufferFloat         Account;

CBufferFloat         Actions;

CBufferFloat         Gradient;

CBufferFloat         *Result;

vector<float>        check;

//---

COpenCLMy           *OpenCL;

//+------------------------------------------------------------------+

//| Expert initialization function                                   |

//+------------------------------------------------------------------+

int OnInit()

  {

//---

   ResetLastError();

   if(!LoadTotalBase())

     {

      PrintFormat("Error of load study data: %d", GetLastError());

      return INIT_FAILED;

     }

//--- load models

   float temp;

   if(!StateEncoder.Load(FileName + "Enc.nnw", temp, temp, temp, dtStudied, true) ||

      !Critic1.Load(FileName + "Crt1.nnw", temp, temp, temp, dtStudied, true) ||

      !Critic2.Load(FileName + "Crt2.nnw", temp, temp, temp, dtStudied, true))

     {

      Print("Cann't load Critic models");

      return INIT_FAILED;

     }

   if(!Actor.Load(FileName + "Act.nnw", temp, temp, temp, dtStudied, true))

     {

      Print("Init new models");

      CArrayObj *actor = new CArrayObj();

      CArrayObj *critic = new CArrayObj();

      if(!CreateDescriptions(actor, critic, critic))

        {

         delete actor;

         delete critic;

         return INIT_FAILED;

        }

      if(!Actor.Create(actor))

        {

         delete actor;

         delete critic;

         return INIT_FAILED;

        }

      delete actor;

      delete critic;

     }

//---

   OpenCL = Actor.GetOpenCL();

   Critic1.SetOpenCL(OpenCL);

   Critic2.SetOpenCL(OpenCL);

   StateEncoder.SetOpenCL(OpenCL);

//---

   StateEncoder.TrainMode(false);

   Critic1.TrainMode(false);

   Critic2.TrainMode(false);

//---

   Actor.getResults(Result);

   if(Result.Total() != NActions)

     {

      PrintFormat("The scope of the actor does not match the actions count (%d <> %d)", NActions, Result.Total());

      return INIT_FAILED;

     }

//---

   StateEncoder.GetLayerOutput(0, Result);

   if(Result.Total() != (HistoryBars * BarDescr))

     {

      PrintFormat("Input size of State Encoder doesn't match state description (%d <> %d)", Result.Total(), (HistoryBars * BarDescr));

      return INIT_FAILED;

     }

//---

   StateEncoder.getResults(Result);

   int latent_state = Result.Total();

   Critic1.GetLayerOutput(0, Result);

   if(Result.Total() != latent_state)

     {

      PrintFormat("Input size of Critic1 doesn't match output State Encoder (%d <> %d)", Result.Total(), latent_state);

      return INIT_FAILED;

     }

//---

   Critic2.GetLayerOutput(0, Result);

   if(Result.Total() != latent_state)

     {

      PrintFormat("Input size of Critic2 doesn't match output State Encoder (%d <> %d)", Result.Total(), latent_state);

      return INIT_FAILED;

     }

//---

   Actor.GetLayerOutput(0, Result);

   if(Result.Total() != latent_state)

     {

      PrintFormat("Input size of Actor doesn't match output State Encoder (%d <> %d)", Result.Total(), latent_state);

      return INIT_FAILED;

     }

//---

   Gradient.BufferInit(AccountDescr, 0);

//---

   if(!EventChartCustom(ChartID(), 1, 0, 0, "Init"))

     {

      PrintFormat("Error of create study event: %d", GetLastError());

      return INIT_FAILED;

     }

//---

   return(INIT_SUCCEEDED);

  }

//+------------------------------------------------------------------+

//| Expert deinitialization function                                 |

//+------------------------------------------------------------------+

void OnDeinit(const int reason)

  {

//---

   if(!(reason == REASON_INITFAILED || reason == REASON_RECOMPILE))

      Actor.Save(FileName + "Act.nnw", 0, 0, 0, TimeCurrent(), true);

   delete Result;

   delete OpenCL;

  }

//+------------------------------------------------------------------+

//| ChartEvent function                                              |

//+------------------------------------------------------------------+

void OnChartEvent(const int id,

                  const long &lparam,

                  const double &dparam,

                  const string &sparam)

  {

//---

   if(id == 1001)

      Train();

  }

//+------------------------------------------------------------------+

//| Train function                                                   |

//+------------------------------------------------------------------+

void Train(void)

  {

//---

   vector<float> probability = GetProbTrajectories(Buffer, 0.9);

//---

   vector<float> rewards, rewards1, rewards2, target_reward;

   vector<float> action, action_beta;