You can definitely try to regularize against ruleset changes by generating a bunch of cards and making the agent play in randomized subsets of those cards.

I didn't look for prior work on this, but my estimate is that it's probably within 2-3 orders of magnitude of additional training compared to a static game. (Still a lot!)

▲

hnedeotes 2 hours ago | parent [-]

But wouldn't (couldn't) the model then hallucinate play patterns and get itself into problems when playing against a real opponent?

	▲	xpct an hour ago \| parent [-]
		Well, if your training includes regularization against ruleset changes, the model should simply handle it. (that would be the expensive option, and require vastly more training) When the Dota 2 bot was made, they retrained the bot only partially when new patches came in, so it was definitely cheaper to adapt.