So, I took a few days off to play video games instead of overheating my GPU on model training. I'm starting up again now, but first I decided to change my training data a bit. Mostly I'm annoyed that the NNs are performing so poorly against the smart random player. So, for the next few … Continue reading Training Data Update
I'm still tracking number of games won during the tournament, but as those results are relative to each other it's hard to see if any absolute progress is being made. So, as previously reported, I started playing each model against the Smart Random player for 100 games and seeing how often the NN won. This will … Continue reading Results by Depth and Width and Depth (Rounds 11-15)
The first thing to notice is that the AI has finally learned to take the center column. The second thing to notice is that he pursued a win that simply couldn't be achieved, continuing vertically in the center column. The third thing to notice is that it's final move, in column 2, is what allowed … Continue reading Playing 3×100 after Round 15
Round 11: Round 12: Round 13: Round 14: Round 15:
Skynetting Myself 