Appendix A Source codes

Specifically, we average the scores over 100 episodes evaluated on confounded environments for each random seed. We use Adam optimizer with the learning rate of 3e-4. Note that other regularization baselines are based on BC. In particular, OREO achieves the mean HNS of 114.9%, while Figure 9: We compare OREO to CCIL with environment interaction, on 6 confounded Atari environments. We investigate the possibility of applying OREO to other IL methods.