Comment by feoren
3 years ago
I don't feel like this is a good application of predictive networks, but maybe I'm wrong. Tiny changes in wording of a card can make or break an exploitable synergy. You can say "tigers basically look like this, ish" to an image recognizer, but you can't just say "decks that look kinda like this are super strong; decks that look kinda like that are super weak". I'd think the best approach here would be to have an agent just play the deck against other decks a million times with an evolving strategy. I know if you say the term "genetic algorithm" nowadays you get laughed at and branded as an old-fashioned ignoramus who doesn't understand real AI, but sometimes the answer is to get off the bandwagon.
Magic the Gathering cards have pretty standard and predictable wording and keywords. Not sure it could understand everything, but there would be easy patterns that apply to hundreds or thousands of cards.
Fun fact, the cards are standard enough that for MTG Arena, they actually parse them with feature grammars instead of neural networks.
Oh wow really? I figured they had a domain specific language to program the card interactions. Pretty cool they can parse the text directly.
Can you elaborate or point to a source? This is highly relevant to my interests.
I don't think GP is saying we'd have difficulty encoding the cards. I think they're saying that deck performance is very sensitive to minor changes, and dependent on a lot of interactions between sets of cards.
To add to that point, decks can be good or bad based on the ecosystem (meta) they're playing in. A deck that aims to rush you down might be great in a meta where players expect slow decks, but terrible in a meta where many decks have means of healing themselves.
Exactly - the landscape of decks is extremely chaotic and I can't imagine gradient descent having any real power to discover the few towering singularities of super-exploit power-decks when changing a 3 to a 2 in the middle of the effect description of one card would render the same deck just meh. You don't really find exploits by approaching them slowly from a distance.
EDH less so though due to the bigger deck size and 1 copy per card limitation. This means you end up with bigger groups of cards with common synergies vs specific sets of cards you need to draw in regular 60-card.
Sometimes there's subtlety. Well it's a language unto itself, that's why everyone can play with any language cards (except Asian language cards sometimes) no problem. It's mostly image recognition, you see the image and you're like "Oh fuck, that's the last thing I wanted him to play!" And weep a little inside, from the pain of losing alone, no bets really. Never bet on the outcome of a casual game.