GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning

02/22/2021 ∙ by Guy Tennenholtz, et al. ∙ 0

Offline reinforcement learning approaches can generally be divided to proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. We impose a latent representation of states and actions and leverage its intrinsic Riemannian geometry to measure distance of latent samples to the data. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data. We integrate our metrics in a model-based offline optimization framework, in which proximity and uncertainty can be carefully controlled. We illustrate the geodesics on a simple grid-like environment, depicting its natural inherent topology. Finally, we analyze our approach and improve upon contemporary offline RL benchmarks.



There are no comments yet.


page 6

page 13

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.