DeepMind StarCraft II Demonstration [video]

Post by aurelwu » Thu, Jan 24, 2019, 6:57 PM UTC

codeflo wrote: post #10

samcday wrote: post #5

Earlier quoted context omitted.

but he's currently not even in the top 50 even with his main race Does that really matter? AFAICT he's in the top #100 [1]. For a game as complex as SC2, it's pretty significant that DeepMind is showing these kinds of results already. It's only going to improve from here right? [1]: https://www.gosugamers.net/starcraft2/players/14064-tlo

With Protoss, he's not remotely near that. And that does matter if you intend to make huge a press release in the shape of "DeepMind AI beats top pro player". We'll see in an hour if that's what they're going for.

Post by codeflo » Thu, Jan 24, 2019, 7:03 PM UTC

aurelwu wrote: post #11

codeflo wrote: post #10

Earlier quoted context omitted.

With Protoss, he's not remotely near that. And that does matter if you intend to make huge a press release in the shape of "DeepMind AI beats top pro player". We'll see in an hour if that's what they're going for.

there is a LiquidMana coming on now ;)

Post by soohyung » Thu, Jan 24, 2019, 7:03 PM UTC

jpdus wrote: post #4

I am somewhat disappointed that they stream only hand-picked replays. For a big, announced presentation, they should be at a stage to stream live games (like OpenAI did with Dota). However, apart from that great work by Deepmind and I am excited to follow the progress in this area.

Post by archgoon » Thu, Jan 24, 2019, 7:16 PM UTC

codeflo wrote: post #3

I'm starting to get annoyed with these DeepMind publicity stunts. They don't release any code, and don't let anyone verify their results. Their chess AI beating Stockfish involved some at least a bit questionable setup. And here? I'm a big fan of TLO, but he's currently not even in the top 50 even with his main race. With Protoss, he's clearly making amateur-level mistakes. Why choose this setting to show off your su…

Post by gambler » Thu, Jan 24, 2019, 7:25 PM UTC

Sweetness wrote: post #7

codeflo wrote: post #3

I'm starting to get annoyed with these DeepMind publicity stunts. They don't release any code, and don't let anyone verify their results. Their chess AI beating Stockfish involved some at least a bit questionable setup. And here? I'm a big fan of TLO, but he's currently not even in the top 50 even with his main race. With Protoss, he's clearly making amateur-level mistakes. Why choose this setting to show off your su…

Because it's still insanely impressive. I would have been blown away if the AI was merely at the platinum level. This is an AI playing starcraft. Starcraft!