# What do state features mean in the context of inverse RL?

I am reading Zeibart's Inverse RL paper, and it states -

The agent is assumed to be attempting to optimize some function that linearly maps the features of each state, $$f_{sj} \in \mathbb{R}^k$$, to a state reward value representing the agent’s utility for visiting that state."

Can someone please give me an example of state features? I would highly appreciate it if it is in the context of this GitHub repo, wherein the author coded the feature_matrix as a diagonal matrix of shape $$N \times D$$, where $$N$$ represents states and $$D$$ features.

• Yeah i was also facing this problem. If you knew this plz talk with me here. Jan 30 at 5:10