If you are interested in this, I maintain a list of boardgame-solving related research at <a href="https://github.com/captn3m0/boardgame-research" rel="nofollow">https://github.com/captn3m0/boardgame-research</a>, with sections for specific games.<p>This looks really interesting. It would be a good project to test this against a general card-playing framework to easily test it on a variety of imperfect-information games based on playing cards.
This is clearly part of DeepMind's long-game plan to achieve world domination through board game mastery. Naming the new algorithm after the book is a real tip of their hand...<p><a href="https://en.wikipedia.org/wiki/The_Player_of_Games" rel="nofollow">https://en.wikipedia.org/wiki/The_Player_of_Games</a>
I really like seeing references to the Culture series when naming things:<p><a href="https://en.m.wikipedia.org/wiki/The_Player_of_Games" rel="nofollow">https://en.m.wikipedia.org/wiki/The_Player_of_Games</a>
This is a great result, but you can see that it's more of a theoretical case because of this: "converging to perfect play as available computation time and approximation capacity increases." That is true for pretty much all current deep reinforcement learning algorithms.<p>The practical question is: How much computation do you need to get useful results? Alpha Go Zero is impressive mathematics, but who is willing to spend $1mio daily for months to train it? IMPALA (another Google one) can learn almost all Atari games, but you need a head node with 256 TPU cores and 1000+ evaluation workers to replicate the timings from the paper.
Comparing against Stockfish 8 in a paper released today and labeling it as "Stockfish" is bordering on being dishonest. The current stockfish version (14) would make AlphaZero look bad, so they don't include it ...
I think this is a good step forward that generalizes an algorithm to play both perfect and imperfect information games. However, table 9 shows (I believe it shows, it is not the most intuitive form), that other AIs (Deepstack, ReBeL, and Supremus) eat its lunch at poker. It also performs worse than AlphaZero at perfect information games. So, while a nice generalizing framework, probably will not be what you use in practice.
I didn't even know about the book until I read the comments here, I thought it was a reference to the Grimes song. Funny coincidence the song and the engine would appear so close in time to one another.
This seems like a significant milestone in AI. I mean what can't an agent with mastery of "guided search, learning, and game-theoretic reasoning" accomplish?
Anyone else surprised to see that Demis Hassabis didn't have a hand in this research? Given his background as a player of many games, and involvement in a lot of their research.
I want to see deepmind make a bot to play team based first person shooters like csgo and rainbow6 siege, to stack up five of them against a team of professional players.
It would be awesome to have two interacting communities: AI experts building open source general game playing engines, and gaming fans writing pluggable rule specifications and UIs for popular games.<p>A bit of googling shows that there is a General Game Playing AI community with their own Game Description Language. I never really encountered them before, and the DeepMind paper does not cite them, either.