TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Player of Games

364 pointsby vatueilover 3 years ago

22 comments

captn3m0over 3 years ago
If you are interested in this, I maintain a list of boardgame-solving related research at <a href="https:&#x2F;&#x2F;github.com&#x2F;captn3m0&#x2F;boardgame-research" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;captn3m0&#x2F;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.
评论 #29482595 未加载
评论 #29486390 未加载
评论 #29492051 未加载
评论 #29489783 未加载
评论 #29482125 未加载
sdenton4over 3 years ago
This is clearly part of DeepMind&#x27;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:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Player_of_Games" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Player_of_Games</a>
评论 #29482357 未加载
评论 #29485104 未加载
评论 #29482090 未加载
评论 #29482941 未加载
评论 #29481958 未加载
评论 #29482923 未加载
评论 #29482045 未加载
sfkgtborover 3 years ago
I really like seeing references to the Culture series when naming things:<p><a href="https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;The_Player_of_Games" rel="nofollow">https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;The_Player_of_Games</a>
评论 #29482155 未加载
评论 #29481986 未加载
评论 #29481830 未加载
评论 #29482734 未加载
评论 #29482088 未加载
fxtentacleover 3 years ago
This is a great result, but you can see that it&#x27;s more of a theoretical case because of this: &quot;converging to perfect play as available computation time and approximation capacity increases.&quot; 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.
评论 #29482553 未加载
评论 #29490009 未加载
tsbinzover 3 years ago
Comparing against Stockfish 8 in a paper released today and labeling it as &quot;Stockfish&quot; is bordering on being dishonest. The current stockfish version (14) would make AlphaZero look bad, so they don&#x27;t include it ...
评论 #29483697 未加载
评论 #29485486 未加载
评论 #29484217 未加载
评论 #29486963 未加载
评论 #29484025 未加载
评论 #29489223 未加载
hervatureover 3 years ago
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.
SuoDuanDaoover 3 years ago
I didn&#x27;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.
评论 #29484176 未加载
ArtWombover 3 years ago
This seems like a significant milestone in AI. I mean what can&#x27;t an agent with mastery of &quot;guided search, learning, and game-theoretic reasoning&quot; accomplish?
评论 #29488477 未加载
WilliamDampierover 3 years ago
so this is what Grimes latest song is about?
评论 #29486281 未加载
评论 #29483783 未加载
pixelpoetover 3 years ago
Anyone else surprised to see that Demis Hassabis didn&#x27;t have a hand in this research? Given his background as a player of many games, and involvement in a lot of their research.
评论 #29545314 未加载
BeenChillingover 3 years ago
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.
评论 #29483204 未加载
评论 #29488525 未加载
评论 #29484336 未加载
skinner_over 3 years ago
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.
评论 #29491316 未加载
cab404over 3 years ago
SCP-like name for SCP-like neural network.<p>&quot;SCP-29123 Player Of Games&quot;
wiz21cover 3 years ago
Couldn&#x27;t resist :<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=-1F7vaNP9w0" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=-1F7vaNP9w0</a>
antonpuzover 3 years ago
Anyone knows whether the agent is publicly available?
simonebrunozziover 3 years ago
Can this be realistically used by game companies to provide a much better AI experience for strategy games?
bkartalover 3 years ago
Impressive work! Most authors, if not all, are from DeepMind Edmonton office.
评论 #29481976 未加载
crhutchinsover 3 years ago
I&#x27;ll try to look into a brighter light into this one.
RivieraKidover 3 years ago
Wow, it can beat a good poker bot, that is impressive.
loxiasover 3 years ago
Psh, wake me when it can play Mao. ;)
wly_cdgrover 3 years ago
The future is so depressing
评论 #29482148 未加载
mudlusover 3 years ago
Yawn, show me a computer that game make fun games
评论 #29484119 未加载
评论 #29518246 未加载
评论 #29492156 未加载
评论 #29495011 未加载