Unless I'm misreading something, it appears that the linked paper appears to use...

		HanClinto on Dec 8, 2023 \| parent \| context \| favorite \| on: Fine-tuning Mistral 7B on Magic the Gathering Draf... Unless I'm misreading something, it appears that the linked paper appears to use one-hot encoding to represent each of the cards -- not any learned embedding to represent each card -- unless I'm misunderstanding what you mean by "representation learning"?