private static string RenderHighestValueAtPosition(IStateActionValues values, Position pos)
{
var posValues = values.ActionValues(pos).Select(av => av.Item2).ToList();
if (posValues.Count == 0)
{
return(" ");
}
const string format = "{0:0000.0;-000.0}";
return(string.Format(format, posValues.Max()));
}
private static IEnumerable <Position> GreedyPath(
CliffWalkingEnvironment env, IStateActionValues values)
{
var currentPosition = env.Reset();
var isDone = false;
while (!isDone)
{
yield return(currentPosition);
var bestAction = values
.ActionValues(currentPosition)
.OrderBy(av => av.Item2)
.Last().Item1;
var(observation, _, done) = env.Step(bestAction);
currentPosition = observation;
isDone = done;
}
yield return(currentPosition);
}