/// <summary>
/// Steps the gym one or more steps with a given action.
/// </summary>
/// <param name="nAction">Specifies the action to run.</param>
/// <param name="nSteps">Specifies the number of steps to run the action.</param>
/// <returns>A tuple containing a double[] with the data, a double with the reward and a bool with the terminal state is returned.</returns>
public CurrentState Step(int nAction, int nSteps = 1)
{
if (m_igym == null)
{
throw new Exception("You must call 'Initialize' first!");
}
for (int i = 0; i < nSteps - 1; i++)
{
m_igym.Step(nAction);
}
Tuple <State, double, bool> state = m_igym.Step(nAction);
bool bIsOpen = (m_nUiId >= 0) ? true : false;
Tuple <Bitmap, SimpleDatum> data = m_igym.Render(bIsOpen, 512, 512, true);
int nDataLen = 0;
SimpleDatum sd = state.Item1.GetData(false, out nDataLen);
Observation obs = new Observation(data.Item1, ImageData.GetImage(data.Item2), m_igym.RequiresDisplayImage, sd.GetData <double>(), state.Item2, state.Item3);
if (bIsOpen)
{
if (m_rgrgActionDistributions != null)
{
overlay(obs.ImageDisplay, m_rgrgActionDistributions);
}
m_gymui.Render(m_nUiId, obs);
Thread.Sleep(m_igym.UiDelay);
}
if (m_igym.SelectedDataType == DATA_TYPE.BLOB)
{
sd = data.Item2;
}
else
{
sd.Clip(nDataLen, null, nDataLen, null);
}
m_state = new Tuple <SimpleDatum, double, bool>(sd, state.Item2, state.Item3);
return(new CurrentState(m_state.Item1.GetData <double>(), m_state.Item2, m_state.Item3));
}
protected override bool getData(GetDataArgs e)
{
Tuple <State, double, bool> state = null;
if (e.Reset)
{
if (m_firststate != null)
{
state = m_firststate;
m_firststate = null;
}
else
{
state = m_igym.Reset();
}
}
if (e.Action >= 0)
{
state = m_igym.Step(e.Action);
}
bool bIsOpen = (m_nUiId >= 0) ? true : false;
int nDataLen = 0;
SimpleDatum stateData = state.Item1.GetData(false, out nDataLen);
e.State = new StateBase(m_igym.GetActionSpace().Count());
e.State.Reward = 0;
e.State.Data = stateData;
e.State.Done = state.Item3;
e.State.IsValid = true;
if (m_sw.Elapsed.TotalMilliseconds > 1000)
{
int nMax = (int)GetProperty("GlobalMaxIterations");
int nIteration = (int)GetProperty("GlobalIteration");
double dfPct = (nMax == 0) ? 0 : (double)nIteration / (double)nMax;
e.OutputLog.Progress = dfPct;
e.OutputLog.WriteLine("(" + dfPct.ToString("P") + ") Global Iteration #" + nIteration.ToString());
m_sw.Restart();
}
return(true);
}
protected override bool getData(GetDataArgs e)
{
Tuple <State, double, bool> state = null;
if (e.Reset)
{
state = m_igym.Reset();
}
if (e.Action >= 0)
{
state = m_igym.Step(e.Action);
}
bool bIsOpen = (m_nUiId >= 0) ? true : false;
Tuple <Bitmap, SimpleDatum> data = m_igym.Render(bIsOpen, 512, 512, true);
int nDataLen = 0;
SimpleDatum stateData = state.Item1.GetData(false, out nDataLen);
Observation obs = new Observation(data.Item1, ImageData.GetImage(data.Item2), m_igym.RequiresDisplayImage, stateData.RealData, state.Item2, state.Item3);
e.State = new StateBase(m_igym.GetActionSpace().Count());
e.State.Reward = obs.Reward;
e.State.Data = data.Item2;
e.State.Done = obs.Done;
e.State.IsValid = true;
if (m_gymui != null && m_nUiId >= 0)
{
m_gymui.Render(m_nUiId, obs);
Thread.Sleep(m_igym.UiDelay);
}
if (m_sw.Elapsed.TotalMilliseconds > 1000)
{
double dfPct = (GlobalEpisodeMax == 0) ? 0 : (double)GlobalEpisodeCount / (double)GlobalEpisodeMax;
e.OutputLog.Progress = dfPct;
e.OutputLog.WriteLine("(" + dfPct.ToString("P") + ") Global Episode #" + GlobalEpisodeCount.ToString() + " Global Reward = " + GlobalRewards.ToString() + " Exploration Rate = " + ExplorationRate.ToString("P") + " Optimal Selection Rate = " + OptimalSelectionRate.ToString("P"));
m_sw.Restart();
}
return(true);
}
