okWarrior_EA/references/MQL5/Experts/CWBC/StudyAgent.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     = 1000;

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

//|                                                                  |

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

STrajectory          Buffer[];

CNet                 Agent;

//---

float                dError;

datetime             dtStudied;

//---

CBufferFloat         State;

CBufferFloat         *Result;

vector<float>        Actions;

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

//| Expert initialization function                                   |

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

int OnInit()

  {

//---

   ResetLastError();

   if(!LoadTotalBase())

     {

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

      return INIT_FAILED;

     }

//--- load models

   float temp;

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

     {

      Print("Init new models");

      CArrayObj *agent = new CArrayObj();

      if(!CreateDescriptions(agent))

        {

         delete agent;

         return INIT_FAILED;

        }

      if(!Agent.Create(agent))

        {

         delete agent;

         return INIT_FAILED;

        }

      delete agent;

     }

//---

   Agent.getResults(Result);

   if(Result.Total() != NActions)

     {

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

      return INIT_FAILED;

     }

//---

   Agent.GetLayerOutput(0, Result);

   if(Result.Total() != (NRewards + BarDescr * NBarInPattern + AccountDescr + TimeDescription + NActions))

     {

      PrintFormat("Input size of Agent doesn't match state description (%d <> %d)", Result.Total(), (NRewards + BarDescr * NBarInPattern + AccountDescr + TimeDescription + NActions));

      return INIT_FAILED;

     }

//---

   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)

  {

//---

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

   delete Result;

  }

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

//| 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)

  {

   float max_reward = 0, quanitle = 0;

   vector<float> std;

   vector<float> probability = GetProbTrajectories(Buffer, max_reward, quanitle, std, 0.95, 0.1f);

   uint ticks = GetTickCount();

//---

   bool StopFlag = false;

   for(int iter = 0; (iter < Iterations && !IsStopped() && !StopFlag); iter ++)

     {

      int tr = SampleTrajectory(probability);

      int i = (int)((MathRand() * MathRand() / MathPow(32767, 2)) * MathMax(Buffer[tr].Total - 2 * HistoryBars - ValueBars, MathMin(Buffer[tr].Total, 20)));

      if(i < 0)

        {

         iter--;

         continue;

        }

      Actions = vector<float>::Zeros(NActions);

      Agent.Clear();

      for(int state = i; state < MathMin(Buffer[tr].Total - 1 - ValueBars, i + HistoryBars * 3); state++)

        {

         //--- History data

         State.AssignArray(Buffer[tr].States[state].state);

         //--- Account description

         float PrevBalance = (state == 0 ? Buffer[tr].States[state].account[0] : Buffer[tr].States[state - 1].account[0]);

         float PrevEquity = (state == 0 ? Buffer[tr].States[state].account[1] : Buffer[tr].States[state - 1].account[1]);

         State.Add((Buffer[tr].States[state].account[0] - PrevBalance) / PrevBalance);

         State.Add(Buffer[tr].States[state].account[1] / PrevBalance);

         State.Add((Buffer[tr].States[state].account[1] - PrevEquity) / PrevEquity);

         State.Add(Buffer[tr].States[state].account[2]);

         State.Add(Buffer[tr].States[state].account[3]);

         State.Add(Buffer[tr].States[state].account[4] / PrevBalance);

         State.Add(Buffer[tr].States[state].account[5] / PrevBalance);

         State.Add(Buffer[tr].States[state].account[6] / PrevBalance);

         //--- Time label

         double x = (double)Buffer[tr].States[state].account[7] / (double)(D'2024.01.01' - D'2023.01.01');

         State.Add((float)MathSin(2.0 * M_PI * x));

         x = (double)Buffer[tr].States[state].account[7] / (double)PeriodSeconds(PERIOD_MN1);

         State.Add((float)MathCos(2.0 * M_PI * x));

         x = (double)Buffer[tr].States[state].account[7] / (double)PeriodSeconds(PERIOD_W1);

         State.Add((float)MathSin(2.0 * M_PI * x));