Goto

Collaborating Authors

 asaf-1




We would like to thank the reviewers for their thorough evaluations and for bringing to our attention some missing

Neural Information Processing Systems

Contrarily, ASAF-1 uses the binary cross entropy loss in Eq. (13) and does not suffer from compounding Can windowed approach be used for GAIL and AIRL? (R1) Our observation is that ASAF-1 is always fastest to learn, e.g., Note however that reports of performance w.r.t wall-clock time should always be taken We will update our related works with your recommendations. Unfortunately, we are not allowed to put an external link in this rebuttal.