This is really sweet. Any odds someone at DeepMind might be working on Paradox Interactive titles like Europa Uiversalis?
AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
331–340 of 459 posts
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#332Earlier quoted context omitted.
But on the other hand, an AI that beats humans using brute force in a game where it makes a ton of difference isn't much fair too.
The funny thing is that once we're talking about the real world, which will come, that incentive actually reverses. At that point the name of the game will be maximizing the advantage the body/infrastructure provides the AI, not minimizing it. Weird.
Yes, since DeepMind chose SC2 for having the right characteristics for mapping to the real world, ie imperfect information and real time response, they should have had at least one run without any speed governors. And maybe another with the CPU limited to some level we might find in an embedded system of near future.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#333Earlier quoted context omitted.
Yes I am curious of this too. What happens if the human has a giant TV screen that can see the whole map at once Or, what if we slow down the game, so that the human can actually pause the game each second and consider what to do next. That's basically what the computer is allowed to do
> Or, what if we slow down the game, so that the human can actually pause the game each second and consider what to do next. That's basically what the computer is allowed to do While this would make it more fair, it would just make the micro game more similar to chess or go. I don't think humans would necessarily win in the end.
Well, are we wanting to test the computers ability to strategize/plan, or their ability to out click humans?
The former is an interesting AI challenge/achievement, the latter is a space in which computers are already known to outperform humans.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#334Every 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.
I don't think the algorithm is changing. The infrastructure, engineering, practice regimens and environments, the training data, the selection of metrics for success, are changing. One can say broadly they are part of the algorithm, but these are learnings for curators of AI that can easily be transferred to other spaces to "generalize" as well.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#335This is really sweet. Any odds someone at DeepMind might be working on Paradox Interactive titles like Europa Uiversalis?
Do you know if there's a good API for paradox games? I have off the top of my head seen extensible mods for games, but I assumed they all were based off of the predefined Clausewitz Engine.
That said, HOI4 could really use some AI love. Right now, I think the AI has a lot of hard coded values (when invasion should happen vs not). One of the potentially beautiful things about modern AI is that if you can clearly define your objectives, it's possible to find a parsimonious analytical solution to solve that problem. I have immense hope that these gaming AI systems will transform the way we game in the future.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#336Earlier quoted context omitted.
I have played both games and a fan of both. Starcraft is definitely more complex than AoE for AI development and that's why the researchers must have chosen it. The complexity of AI depends on how many potential decisions you can make at any point of time. Here are a few reasons why: 1) Starcraft races have completely different build trees and different advantages. This has a large cascading effect of early decisions…
AoE maps are not flat and units have an attack bonus when uphill (and defense penalty when downhill). Top players will place castles on hills for example and micro their units so that they are more elevated than their opponents. AoE has monks which can take control of enemy units. The fact that Starcraft has more micro potential should make AI development easier, not harder. Micro management is a relatively mechanic…
Micro is often written off as a mechanical task, but this is only relevant with expert systems (like microbots).
There is a lot of tactical nuance and understanding that comes in micro, for a neural network/learning algorithm to understand and optimize is actually very impressive just as much as macro.
Knowing it's optimal to blink when your shield runs out before taking hull damage? To dance your weakened stalker to bait your opponent to overextend? To focus fire but not overkill? To wait for a projectile to be mid-air before blinking or picking in a transport? There's so much more to micro than precision and APM.
To your other points, SC maps have lots of ramps and cliffs and high-ground/low-ground impact (no bonuses, but vision constraints and battle surface area and choke points)
AI development is not easier because of micro potential, because it means the AI needs to be prepared to deal with a wider range of effectiveness for any given unit or set of units, they won't always scale linearly in impactfulness or between different player's playstyles
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#337I wonder how useful ai will be in balancing games in the future. Games with more than one race and multiple upgrade paths seems like a nightmare to ensure that things are even for players that are equally skilled. It would be interesting to have a game that would auto-balance itself, especially if you wanted to add extra content without having to worry about throwing everything off.
That's a cool idea but many games already struggle to find a fair balance point at all ranges of human skill, so expanding that range to include AI could just make things more difficult. Maybe there's a way to force the AI to replicate bad players, but I'm not sure what learning objective you would give it to achieve that.
I don't follow gaming balancing too closely, but I (naively) assume there's some reasonable analytical solution to find tuning. Like I would imagine if you're Blizzard and have logs of all the data, you could just regress race attack/defense/movement/etc. stats to find a potential equivalence point.
I suppose there's lots of interactions, but finding "well Zerg beats Protoss X% of the time", you could balance by messing slightly with resources or blanket buff.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#338Earlier quoted context omitted.
Perfect micro bots don't excite me much, because they've existed all along, and it's not an AI task.
The interesting part to me is that, as far as I understand, the AI figured out this strategy by itself, basically deciding that it would be a good way for it to win games, rather than being specifically programmed to do it. That's actually pretty cool! Other than that, I agree, and am also much more interested in what happens when you have a more level playing field (using camera movement rather than API, limiting re…
I think there is some debate about what the neural net did and what was hardcoded. So far all starcraft AIs consist of hardcoded intelligent micro ruled by a neural net that picks one out of less than 100 possible hardcoded choices. And things like "expand", "scout", "group units", "micro" are hardcoded outside of the neural net, part of the API in fact. When the researches said they only used 15 TPUs for 14 days on LSTM, this makes me think they really narrowed down the search space of the neural net and hardcoded a lot of the micro or at least trained separate micro nets.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#339First Go, now Starcraft 2...I fully expect archery or women's golf to be conquered next. Someone at deepmind must have an axe to grind with Korea ;)
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#340This 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…
Totally. What would be interesting to see is a low APM bot that still beats human players. A lot of that macro was unbeatable.