Very cool. I didn't know NNs were capable of such determinism, that's very interesting. Is this a similar effect to overfitting? Also, it's the same model for all the games, right?
> Also, it's the same model for all the games, right
It's a bit unclear but it looks like different models, since they all have different parameter and MAC counts. It would be much more impressive with a single world model that could maybe dream up new games inbetween the games in the training set.
It's a self contained net for each game but the data used for training doesn't overlap with the validation. I think it would be easy to merge them into a single model