Topic
Optimal Transport
Distribution-Matching Imitation Learning
Develops distribution-matching formulations of imitation learning, including sliced-Wasserstein objectives for occupancy matching.
Remained effective under up to 100× demonstration subsampling on Ant and Humanoid.
Hyperbolic Wasserstein Autoencoders
Generative modeling with Wasserstein autoencoders in hyperbolic latent spaces.