//+------------------------------------------------------------------+
//|                                                   Trajectory.mqh |
//|                                                   Copyright DNG® |
//|                                https://www.mql5.com/ru/users/dng |
//+------------------------------------------------------------------+
#property copyright "Copyright DNG®"
#property link      "https://www.mql5.com/ru/users/dng"
#property version   "1.00"
//+------------------------------------------------------------------+
//| Rewards structure                                                |
//|   0     -  Delta Balance                                         |
//|   1     -  Delta Equity ( "-" Drawdown / "+" Profit)             |
//|   2     -  Penalty for no opened positions                         |
//+------------------------------------------------------------------+
#include "..\RL\FQF.mqh"
//---
#define        HistoryBars             48             //Depth of history
#define        BarDescr                9              //Elements for 1 bar description
#define        NBarInPattern           1              //Bars for 1 pattern description
#define        AccountDescr            8              //Account description
#define        NActions                6              //Number of possible Actions
#define        TimeDescription         4
#define        LatentCount             1024
#define        LatentLayer             2
#define        EmbeddingSize           32
#define        Buffer_Size             6500
#define        DiscFactor              0.99f
#define        FileName                "OPPO"
#define        MaxReplayBuffer         500
#define        MaxSL                   1000
#define        MaxTP                   1000
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
struct STrajectory;
extern STrajectory          Buffer[];
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
struct SState
  {
   float             state[BarDescr * NBarInPattern];
   float             account[AccountDescr];
   float             action[NActions];
   float             scheduler[EmbeddingSize];
   //---
                     SState(void);
   //---
   bool              Save(int file_handle);
   bool              Load(int file_handle);
   //---
   void              Clear(void)
     {
      ArrayInitialize(state, 0);
      ArrayInitialize(account, 0);
      ArrayInitialize(action, 0);
      ArrayInitialize(scheduler, 0);
     }
   //--- overloading
   void              operator=(const SState &obj)
     {
      ArrayCopy(state, obj.state);
      ArrayCopy(account, obj.account);
      ArrayCopy(action, obj.action);
      ArrayCopy(scheduler, obj.scheduler);
     }
  };
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
SState::SState(void)
  {
   ArrayInitialize(state, 0);
   ArrayInitialize(account, 0);
   ArrayInitialize(action, 0);
   ArrayInitialize(scheduler, 0);
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool SState::Save(int file_handle)
  {
   if(file_handle == INVALID_HANDLE)
      return false;
//---
   int total = ArraySize(state);
   if(FileWriteInteger(file_handle, total) < sizeof(int))
      return false;
   for(int i = 0; i < total; i++)
      if(FileWriteFloat(file_handle, state[i]) < sizeof(float))
         return false;
//---
   total = ArraySize(account);
   if(FileWriteInteger(file_handle, total) < sizeof(int))
      return false;
   for(int i = 0; i < total; i++)
      if(FileWriteFloat(file_handle, account[i]) < sizeof(float))
         return false;
//---
   total = ArraySize(action);
   if(FileWriteInteger(file_handle, total) < sizeof(int))
      return false;
   for(int i = 0; i < total; i++)
      if(FileWriteFloat(file_handle, action[i]) < sizeof(float))
         return false;
//---
   total = ArraySize(scheduler);
   if(FileWriteInteger(file_handle, total) < sizeof(int))
      return false;
   for(int i = 0; i < total; i++)
      if(FileWriteFloat(file_handle, scheduler[i]) < sizeof(float))
         return false;
//---
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool SState::Load(int file_handle)
  {
   if(file_handle == INVALID_HANDLE)
      return false;
   if(FileIsEnding(file_handle))
      return false;
//---
   int total = FileReadInteger(file_handle);
   if(total != ArraySize(state))
      return false;
//---
   for(int i = 0; i < total; i++)
     {
      if(FileIsEnding(file_handle))
         return false;
      state[i] = FileReadFloat(file_handle);
     }
//---
   total = FileReadInteger(file_handle);
   if(total != ArraySize(account))
      return false;
//---
   for(int i = 0; i < total; i++)
     {
      if(FileIsEnding(file_handle))
         return false;
      account[i] = FileReadFloat(file_handle);
     }
//---
   total = FileReadInteger(file_handle);
   if(total != ArraySize(action))
      return false;
//---
   for(int i = 0; i < total; i++)
     {
      if(FileIsEnding(file_handle))
         return false;
      action[i] = FileReadFloat(file_handle);
     }
//---
   total = FileReadInteger(file_handle);
   if(total != ArraySize(scheduler))
      return false;
//---
   for(int i = 0; i < total; i++)
     {
      if(FileIsEnding(file_handle))
         return false;
      scheduler[i] = FileReadFloat(file_handle);
     }
//---
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
struct STrajectory
  {
   SState            States[Buffer_Size];
   int               Total;
   double            Profit;
   //---
                     STrajectory(void);
   //---
   bool              Add(SState &state);
   void              ClearFirstN(const int n);
   //---
   bool              Save(int file_handle);
   bool              Load(int file_handle);
   //--- overloading
   void              operator=(const STrajectory &obj)
     {
      Total = obj.Total;
      Profit = obj.Profit;
      for(int i = 0; i < Buffer_Size; i++)
         States[i] = obj.States[i];
     }
  };
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
STrajectory::STrajectory(void)  :   Total(0),
   Profit(0)
  {
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool STrajectory::Save(int file_handle)
  {
   if(file_handle == INVALID_HANDLE)
      return false;
//---
   if(FileWriteInteger(file_handle, Total) < sizeof(int))
      return false;
   if(FileWriteDouble(file_handle, Profit) < sizeof(float))
      return false;
   for(int i = 0; i < Total; i++)
      if(!States[i].Save(file_handle))
         return false;
//---
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool STrajectory::Load(int file_handle)
  {
   if(file_handle == INVALID_HANDLE)
      return false;
//---
   Total = FileReadInteger(file_handle);
   if(FileIsEnding(file_handle) || Total >= ArraySize(States))
      return false;
   Profit = FileReadDouble(file_handle);
//---
   for(int i = 0; i < Total; i++)
      if(!States[i].Load(file_handle))
         return false;
//---
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool STrajectory::Add(SState &state)
  {
   if(Total + 1 >= ArraySize(States))
      return false;
   States[Total] = state;
   Total++;
//---
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
void STrajectory::ClearFirstN(const int n)
  {
   for(int i = 0; i < Buffer_Size - n; i++)
      States[i] = States[i + n];
   Total = MathMax(0, Buffer_Size - n);
   for(int i = Total; i < Buffer_Size; i++)
      States[i].Clear();
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
int SaveTotalBase(int min_bars)
  {
   int total = ArraySize(Buffer);
   if(total < 0)
      return 0;
   int handle = FileOpen(FileName + ".bd", FILE_WRITE | FILE_BIN | FILE_COMMON);
   if(handle < 0)
      return 0;
   int indexes[MaxReplayBuffer];
   int count = 0;
   for(int i = total - 1; i >= 0; i--)
     {
      if(Buffer[i].Total < min_bars)
         continue;
      indexes[count] = i;
      count++;
     }
   if(FileWriteInteger(handle, count) < INT_VALUE)
     {
      FileClose(handle);
      return 0;
     }
   for(int i = count - 1; i >= 0; i--)
      if(!Buffer[indexes[i]].Save(handle))
        {
         FileClose(handle);
         return (count - (i + 1));
        }
   FileFlush(handle);
   FileClose(handle);
//---
   return count;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool LoadTotalBase(void)
  {
   int handle = FileOpen(FileName + ".bd", FILE_READ | FILE_BIN | FILE_COMMON | FILE_SHARE_READ);
   if(handle < 0)
      return false;
   int total = FileReadInteger(handle);
   if(total <= 0)
     {
      FileClose(handle);
      return false;
     }
   if(ArrayResize(Buffer, total) < total)
     {
      FileClose(handle);
      return false;
     }
   for(int i = 0; i < total; i++)
      if(!Buffer[i].Load(handle))
        {
         FileClose(handle);
         return false;
        }
   FileClose(handle);
//---
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool CreateAgentDescriptions(CArrayObj *agent)
  {
//---
   CLayerDescription *descr;
//---
   if(!agent)
     {
      agent = new CArrayObj();
      if(!agent)
         return false;
     }
//--- Agent
   agent.Clear();
//--- Input layer
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   uint prev_count = descr.count = (BarDescr * NBarInPattern + AccountDescr + TimeDescription + NActions + EmbeddingSize);
   descr.activation = None;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 1
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBatchNormOCL;
   descr.count = prev_count;
   descr.batch = 1000;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 2
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronEmbeddingOCL;
   prev_count = descr.count = HistoryBars;
     {
      int temp[] = {BarDescr * NBarInPattern, AccountDescr, TimeDescription, NActions, EmbeddingSize};
      ArrayCopy(descr.windows, temp);
     }
   uint prev_wout = descr.window_out = EmbeddingSize;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 3
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronSoftMaxOCL;
   descr.count = EmbeddingSize;
   descr.step = prev_count * 5;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 4
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronMLMHAttentionOCL;
   prev_count = descr.count = prev_count * 5;
   descr.window = EmbeddingSize;
   descr.step = 8;
   descr.window_out = 32;
   descr.layers = 4;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 5
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronSoftMaxOCL;
   descr.count = EmbeddingSize;
   descr.step = prev_count;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 6
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronConvOCL;
   prev_count = descr.count = prev_count;
   descr.window = EmbeddingSize;
   descr.step = EmbeddingSize;
   prev_wout = descr.window_out = EmbeddingSize;
   descr.optimization = ADAM;
   descr.activation = LReLU;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 7
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronSoftMaxOCL;
   descr.count = prev_count;
   descr.step = prev_wout;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 8
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronConvOCL;
   prev_count = descr.count = prev_count;
   descr.window = prev_wout;
   descr.step = prev_wout;
   prev_wout = descr.window_out = prev_wout / 2;
   descr.optimization = ADAM;
   descr.activation = LReLU;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 9
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronSoftMaxOCL;
   descr.count = prev_count;
   descr.step = prev_wout;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 10
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   descr.count = LatentCount;
   descr.optimization = ADAM;
   descr.activation = LReLU;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 11
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   prev_count = descr.count = LatentCount;
   descr.activation = LReLU;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 12
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   descr.count = LatentCount;
   descr.activation = LReLU;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 13
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   descr.count = NActions;
   descr.activation = SIGMOID;
   descr.optimization = ADAM;
   if(!agent.Add(descr))
     {
      delete descr;
      return false;
     }
//---
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool CreateSchedulerDescriptions(CArrayObj *scheduler)
  {
//---
   CLayerDescription *descr;
//---
   if(!scheduler)
     {
      scheduler = new CArrayObj();
      if(!scheduler)
         return false;
     }
//--- Scheduler
   scheduler.Clear();
//--- Input layer
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   uint prev_count = descr.count = (BarDescr * NBarInPattern + AccountDescr + TimeDescription + NActions);
   descr.activation = None;
   descr.optimization = ADAM;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 1
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBatchNormOCL;
   descr.count = prev_count;
   descr.batch = 1000;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 2
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronEmbeddingOCL;
   prev_count = descr.count = HistoryBars;
     {
      uint temp[] = {BarDescr * NBarInPattern, AccountDescr, TimeDescription, NActions};
      ArrayCopy(descr.windows, temp);
     }
   uint prev_wout = descr.window_out = EmbeddingSize;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 3
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronSoftMaxOCL;
   descr.count = EmbeddingSize;
   descr.step = prev_count * 4;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 4
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronMLMHAttentionOCL;
   prev_count = descr.count = prev_count * 4;
   descr.window = EmbeddingSize;
   descr.step = 8;
   descr.window_out = 32;
   descr.layers = 4;
   descr.optimization = ADAM;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 5
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronSoftMaxOCL;
   descr.count = EmbeddingSize;
   descr.step = prev_count;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 6
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   descr.count = LatentCount;
   descr.optimization = ADAM;
   descr.activation = LReLU;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//--- layer 7
   if(!(descr = new CLayerDescription()))
      return false;
   descr.type = defNeuronBaseOCL;
   prev_count = descr.count = EmbeddingSize;
   descr.activation = None;
   descr.optimization = ADAM;
   if(!scheduler.Add(descr))
     {
      delete descr;
      return false;
     }
//---
   return true;
  }
#ifndef Study
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool IsNewBar(void)
  {
   static datetime last_bar = 0;
   if(last_bar >= iTime(Symb.Name(), TimeFrame, 0))
      return false;
//---
   last_bar = iTime(Symb.Name(), TimeFrame, 0);
   return true;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool CloseByDirection(ENUM_POSITION_TYPE type)
  {
   int total = PositionsTotal();
   bool result = true;
   for(int i = total - 1; i >= 0; i--)
     {
      if(PositionGetSymbol(i) != Symb.Name())
         continue;
      if(PositionGetInteger(POSITION_TYPE) != type)
         continue;
      result = (Trade.PositionClose(PositionGetInteger(POSITION_TICKET)) && result);
     }
//---
   return result;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool TrailPosition(ENUM_POSITION_TYPE type, double sl, double tp)
  {
   int total = PositionsTotal();
   bool result = true;
//---
   for(int i = 0; i < total; i++)
     {
      if(PositionGetSymbol(i) != Symb.Name())
         continue;
      if(PositionGetInteger(POSITION_TYPE) != type)
         continue;
      bool modify = false;
      double psl = PositionGetDouble(POSITION_SL);
      double ptp = PositionGetDouble(POSITION_TP);
      switch(type)
        {
         case POSITION_TYPE_BUY:
            if((sl - psl) >= Symb.Point())
              {
               psl = sl;
               modify = true;
              }
            if(MathAbs(tp - ptp) >= Symb.Point())
              {
               ptp = tp;
               modify = true;
              }
            break;
         case POSITION_TYPE_SELL:
            if((psl - sl) >= Symb.Point())
              {
               psl = sl;
               modify = true;
              }
            if(MathAbs(tp - ptp) >= Symb.Point())
              {
               ptp = tp;
               modify = true;
              }
            break;
        }
      if(modify)
         result = (Trade.PositionModify(PositionGetInteger(POSITION_TICKET), psl, ptp) && result);
     }
//---
   return result;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
bool ClosePartial(ENUM_POSITION_TYPE type, double value)
  {
   if(value <= 0)
      return true;
//---
   for(int i = 0; (i < PositionsTotal() && value > 0); i++)
     {
      if(PositionGetSymbol(i) != Symb.Name())
         continue;
      if(PositionGetInteger(POSITION_TYPE) != type)
         continue;
      double pvalue = PositionGetDouble(POSITION_VOLUME);
      if(pvalue <= value)
        {
         if(Trade.PositionClose(PositionGetInteger(POSITION_TICKET)))
           {
            value -= pvalue;
            i--;
           }
        }
      else
        {
         if(Trade.PositionClosePartial(PositionGetInteger(POSITION_TICKET), value))
            value = 0;
        }
     }
//---
   return (value <= 0);
  }
#endif
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
vector<double> GetProbTrajectories(STrajectory &buffer[], float lanbda)
  {
   ulong total = buffer.Size();
   vector<double> rewards = vector<double>::Zeros(total);
   for(ulong i = 0; i < total; i++)
      rewards[i]=Buffer[i].Profit;
   double std = rewards.Std();
   double max_profit = rewards.Max();
//---
   vector<double> sorted = rewards;
   bool sort = true;
   while(sort)
     {
      sort = false;
      for(ulong i = 0; i < sorted.Size() - 1; i++)
         if(sorted[i] > sorted[i + 1])
           {
            double temp = sorted[i];
            sorted[i] = sorted[i + 1];
            sorted[i + 1] = temp;
            sort = true;
           }
     }
//---
   double min = rewards.Min() - 0.1 * std;
   if(max_profit > min)
     {
      double k = sorted.Percentile(90) - max_profit;
      vector<double> multipl = MathAbs(rewards - max_profit) / (k == 0 ? -std : k);
      multipl = exp(multipl);
      rewards = (rewards - min) / (max_profit - min);
      rewards = rewards / (rewards + lanbda) * multipl;
      rewards.ReplaceNan(0);
     }
   else
      rewards.Fill(1);
   rewards = rewards / rewards.Sum();
   rewards = rewards.CumSum();
//---
   return rewards;
  }
//+------------------------------------------------------------------+
//|                                                                  |
//+------------------------------------------------------------------+
int SampleTrajectory(vector<double> &probability)
  {
//--- check
   ulong total = probability.Size();
   if(total <= 0)
      return -1;
//--- randomize
   double rnd = double(MathRand()) / 32767.0;
//--- search
   if(rnd <= probability[0] || total == 1)
      return 0;
   if(rnd > probability[total - 2])
      return int(total - 1);
   int result = int(rnd * total);
   if(probability[result] < rnd)
      while(probability[result] < rnd)
         result++;
   else
      while(probability[result - 1] >= rnd)
         result--;
//--- return result
   return result;
  }
//+------------------------------------------------------------------+