The gameplay was really interesting - i wonder if we'll start seeing the over-saturation of the main prior to first expand in pro games?
AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
71–80 of 459 posts
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#72Every year or so we get another huge advance... Well, more accurately, something comes along to benchmark the state of AI research against a human activity. Then come the HN comments. For Alpha Go: Oh this is impressive but can't generalize. Wake me up when it doesn't have to have information precoded/doesn't learn from human players For alpha go 0: So this is cool but not amazing because they're all perfect informat…
Note that this approach is very dissimilar to Alpha Go or Alpha Go 0. So it's true that they did not generalize...
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#73Can anyone who has a full context compare this to OpenAI's work on Dota 2? Which is more impressive, both in how far along it is and the relative game difficulty?
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#74This is really impressive, I didn't expect starcraft to be played this well by a machine learning based AI. I'm excited to read the paper when it comes out! That said, I'm not sure I agree that it was winning mainly due to better decision making. For context, I've been ranked in the top 0.1% of players and beaten pros in Starcraft 2, and also work as a machine learning engineer. The stalker micro in particular looked…
Also worth noting that it starts by imitation learning from pros. I'd be curious to see if the macro can be learned without imitation; a much harder challenge. Also, playing with full visibility as was mostly the case in the demonstration is quite lame...
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#75Earlier quoted context omitted.
AlphaStar had an average APM of 280, but during battles, it's APM would spike up to ~1500. It's like saying that my car has an average speed of 2mph. Sure, it does - but that's because it spends 23 hours a day sitting in a garage.
Where does it say the APM spiked during battles? If it's using it head-to-head with the human player, then that's bad, but how do you know it's not just herding workers and units individually? I get the analogy but based on the distribution, 75% of the APM for alphastar is below the mean of APM for the human during gameplay. Following that analogy, both cars are on the racetrack, except one is applying acceleration w…
The APM maxed out at 1500 at one point, far in excess of any human, especially considering many human actions are meaningless actions or spam clicks. The AI could win based on inhuman micro with stalkers and blink. I would be far more interested in seeing the agent with a fully realistic camera and fully realistic apm limit.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#76The problem is see is the AI is not better than the human, it's just 1000x faster at APM / macro. It could have a "shit" bo and still win because it's so much faster than a human. It's not really interesting tbh.
Wrong. Did you watch the presentation? Its APM was less than half that of its human opponent. If you aren't going to watch the presentation first, don't try to get involved in the discussion in such a derisive and dismissive way. "It's not really that interesting tbh"....wow. It's something that's never been algorithmically done before, no matter who tried. How can you write that off as "not interesting" as if it's t…
This guy didnt see the game where Alphastar had 1500 apm...
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#77They really should have used BroodWar for deep mind. SCII is way too volatile. Way more gimmicks available that will make it difficult for AI to come close to a human player.
I had a feeling we'd see Brood War elitism in here. There are many, many gimmicks in BW. Every time I watch ASL and KSL, I see numerous quick stomps based on gimmicky builds, just like in SC2, Dota, and every other strategy game with fog of war and a collision of messy strategies.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#78This is really impressive, I didn't expect starcraft to be played this well by a machine learning based AI. I'm excited to read the paper when it comes out! That said, I'm not sure I agree that it was winning mainly due to better decision making. For context, I've been ranked in the top 0.1% of players and beaten pros in Starcraft 2, and also work as a machine learning engineer. The stalker micro in particular looked…
it seems like in some cases at least it didn't have to move the camera (it had direct interfaces) which for some of the stalker micro battles (especially in game 3 or 4?) the battles were larger than the screen space -- it would not have been possible to micro that well if your control interface limited what you can control or where you can place them.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#79Every year or so we get another huge advance... Well, more accurately, something comes along to benchmark the state of AI research against a human activity. Then come the HN comments. For Alpha Go: Oh this is impressive but can't generalize. Wake me up when it doesn't have to have information precoded/doesn't learn from human players For alpha go 0: So this is cool but not amazing because they're all perfect informat…
When your algorithm needs to be changed to generalize, it does not generalize.
If people stopped moving the goalposts and spreading baseless hype, actual AI research would be much father along right now.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#80Earlier quoted context omitted.
Dealing with perfect blinking is basically impossible, since you can blink back your units right before they die. Stalkers are balanced around the fact that HUMANS have limits to how well they can micro.
I'm also excited to see the future of this bot when they demonstrate a terran AI with near-perfect marine/stim/medivac micro.
Perfect micro bots don't excite me much, because they've existed all along, and it's not an AI task.