This is an old revision of the document!

We use L1 as loss function ℓ instead of the mean squared error (MSE), as it is more correlated to driving performance [11]. As our NoCrash benchmark consists of complex realistic driving conditions in the presence of dynamic agents, we collect demonstrations from an expert game AI using privileged information to drive correctly (i.e. always respecting rules of the road and not crashing into any obstacle). Robustness to heavy noise in the demonstrations is beyond the scope of our work, as we aim to explore limitations of behavior cloning methods in spite of good demonstrations. Finally, we pre-trained our perception backbone on ImageNet to reduce initialization variance and benefit from generic transfer learning, a standard practice in deep learning seldom explored for behavior cloning.