public MyTttEnvironment(Dictionary<string, string> options)
: base(options)
{
this.ValidActions=new[] {0,1,2,3,4,5,6,7,8};
int maximumPossibleObservation = 174762;//refact: put into hex
this.ValidObservations = new int[maximumPossibleObservation+1];
for (int i = 0; i < maximumPossibleObservation+1; i++) {
this.ValidObservations[i] = i;
}
// valid_rewards contains {0,1,3,4,5}
this.ValidRewards = (int[])Enum.GetValues(typeof(TictactoeRewardEnum));
base.fill_out_bits();
this.Reward = 0;
this.Reset();
}