2019 Paper Unifies Imitation Learning Methods via Divergence Minimization
Users are excited about the 2019 paper unifying imitation learning methods via divergence minimization because they call it awesome and their favorite from that era.
Most Activity
It got Best Paper at CoRL. In the paper, we decoupled the KL vs state marginal hypothesis explicitly, and empirically shown that matching state marginal mattered more. Link: https://arxiv.org/abs/1911.02256
GKD (2023) paper by @agarwl_ @OlivierBachem is also great!
If you are into OPD, check out our 2019 paper "Divergence Minization Perspective on Imitation Learning". I like to use a single formula/table to explain how methods relate each other, from fundamentals.
Or read DAgger (2010) :)
@shaneguML my favorite paper back in the day 😎
@shaneguML @agarwl_ @OlivierBachem That’s awesome congrats!