So here, for each deck, the AI wouldn’t just be able to obtain a number for how good the deck is-they’d have to have some sub-AI that’s training with that deck, learning how to optimize play with that deck. Not just to see how it does in a variety of situations-but also to learn how to play it, that is, figure out the optimal strategy for playing the cards the deck makes available. pros) do? They create a deck and play it a lot, leveraging their considerable experience. What do human “optimizers” of the game (e.g. To my knowledge, no deck-building game out there enables any easy calculation of the general quality of a given deck. We need to be able to assign a number to how good a try something was, because what the AI is really doing is maximizing that number (or minimizing, whatever). In a large sense, this is all machine learning requires, which certainly makes it very powerful, but it is a hard requirement. To learn, the AI needs to know that attempt 1354235 was better, or worse, than attempt 1354236. It is absolutely crucial, in this scheme, to be able to tell how good a given random try was. Our general approach to AI-“machine learning”-involves the AI trying some random approach, evaluating it for effectiveness, and then doing so over, and over, and over, refining that randomness towards something better and better. There is a major constraint on the way we currently build AI, that makes its application to deck-building games intractable, at least on our current hardware. I defer to anyone who is an expert in AI, but I think currently my expertise is most applicable to this question. I would be interested in any attempts at creating such an AI.įirst, just so you know where I’m coming from, I’m a professional programmer, and I’ve studied AI, but I don’t work with AI professionally, so there are limits to my expertise. And it links to a GitHub with the source.Īs the comments note, this may not be a high quality attempt nor one that handles any card set set you throw at it, but it is an attempt, as per the original post's request: The article goes on to talk about the approach he used. Ooooooooh! Yes, it is as exciting as it sounds! GAs allow us to literally evolve good decks using artificial selection. In particular, I want to talk about an approach to deck building using a technique called genetic algorithms or GAs. If you just want to jump directly to the code, or a deep-dive into the technical nitty-gritty for yourself, you can dig deeper on GitHub. In this article, I want to outline at a high level how I approached this challenge, how my approach works, what went well, and what didn’t. Read along to find out how it works, how you can start using it, and better yet, how you can help make it awesome. (I guess you could make the pool 60 copies of each card legal for the format). A reusable, beautiful artwork box Note: the description is machine translated and might contain errors.Don Goodman-Wilson made a program to build decks given a pool of cards. Ideal for the novice player, but also for the people who have a lot of decks and can use some more from certain basic cards. The 225 cards consist of 100 basic lands and 125 commons and uncommons that will form the basis of many a deck. Do you have what it takes to protect your Guild? From the orderly Azorius Senate, to the hedonistic Cult of Rakdos, the bloodthirsty Gruul Clans, the orthodox Orzhov Syndicate and the constantly evolving Simic Combine, everyone must prepare for the impending storm. Will the erratic peace between the Guilds turn to war? An outsider tries to infiltrate the various Guilds and assassins take care of everyone who stands in their way. All this is packed in a beautiful and handy collection box.Ĭhaos reigns in the streets of Ravnica's endless city. The Deck Builder's Toolkit is a special set with 225 basic cards, 4 boosters from the recent Magic series and a handy guide with game tips.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |