Skill discovery has shown significant progress in unsupervised reinforcement learning.

We provide a closed-form expression for the worst occupation measure.

However, they do not account for transition uncertainty, whereas learning robust policies can be computationally expensive.

In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting.

Sequential decision-making problems typically require significant human supervision and data.

C Results in ALFRED's T ask and New T asks