I am trying to learn utility functions for ships through their AIS data.
I have a lot of data available and plan on focusing on fishing boats.
So far I've researched a lot of IRL algorithms but I'm not sure if I missed a important one that could be applied.
I've found this paper https://journals.sagepub.com/doi/citedby/10.1177/0278364917722396, but I'm not sure if this is really applicable. I would need to transform the ais data as trajectorys, add material from openseamap and plot this to images of trajectories. Or did I misunderstand the paper completely?
My other found approach would be selecting features as position, distance to other vessels and others. And then try to apply continous max entropy deep inverse reinforcement learning.
Is there another approach that may be easier in your eyes?
