Architecture
There are many architectures used in deep learning - you can check out a few here. For AI Arena, we focus on feedforward neural networks. In general they have fewer parameters than convolutional neural networks (CNNs) or recurrent neural networks (RNNs).
This is important to us because we want to reward researchers who come up with better training algorithms, not researchers with more resources to train massive models.
We performed feature engineering to reduce the size of the network needed to train a good policy.
