Slashdot Mirror
Google's DeepMind AI Plans To Take On StarCraft II (venturebeat.com)
An anonymous reader quotes a report from VentureBeat: Google and Blizzard are opening up StarCraft II to anyone who wants to teach artificial intelligence systems how to conduct warfare. Researchers can now use Google's DeepMind A.I. to test various theories for ways that machines can learn to make sense of complicated systems, in this case Blizzard's beloved real-time strategy game. In StarCraft II, players fight against one another by gathering resources to pay for defensive and offensive units. It has a healthy competitive community that is known for having a ludicrously high skill level. But considering that DeepMind A.I. has previously conquered complicated turn-based games like chess and go, a real-time strategy game makes sense as the next frontier. The companies announced the collaboration today at the BlizzCon fan event in Anaheim, California, and Google's DeepMind A.I. division posted a blog about the partnership and why StarCraft II is so ideal for machine-learning research. If you're wondering how much humans will have to teach A.I. about how to play and win at StarCraft, the answer is very little. DeepMind learned to beat the best go players in the world by teaching itself through trial and error. All the researchers had to do was explain how to determine success, and the A.I. can then begin playing games against itself on a loop while always reinforcing any strategies that lead to more success. For StarCraft, that will likely mean asking the A.I. to prioritize how long it survives and/or how much damage it does to the enemy's primary base. Or, maybe, researchers will find that defining success in a more abstract way will lead to better results, discovering the answers to all of this is the entire point of Google and Blizzard teaming up.
Games like Chess, Go, Tic-Tac-Toe always let both players see the complete world state. Armed with that knowledge, it's easy to be systematic and deterministic.
Games like Poker and Starcraft hide part of the world state from each player, forcing them to guess at the parts they can't see. That opens up the possibility of one player bluffing - leading the opponent down the wrong decision tree because he's fooled into thinking the part of the world state he can't see is different from what it really is. I don't think this is something an AI can "solve". Certainly one could optimize it, so that it becomes damn good at guessing when a certain player is bluffing or not. But put it up against a different player and all that "learned" experience becomes useless, or even counter-productive. Or even pit it against the same player who's aware he's playing against the AI which beat him last time, and he'll simply do something he would never normally do to throw off the computer. It's a difficult enough problem that in pretty much all commercial computer games with a fog of war feature, the computer is just programmed to cheat by ignoring the fog and seeing everything.
Let them play Global Nuclear War.
Comment removed based on user account deletion
How about Global Thermonuclear War? https://www.youtube.com/watch?...
We'll make great pets
I would be really interested to see what would the results be if you would get DeepMind playing a game like Civilization, in which cooperation and soft-power can be used to win the game. That could really give all of us some hints on how to manage diplomacy/belligerence in a way that could lead to some interesting thought experiments in the real world.
So it's fine if Google does it, but if I do it, I get a ban for running a bot? Okay then.
Playing games is NOT A.I. This, like "playing" Jeopardy, is just a flashy demo of algorithms and shows us how clueless AI researchers really are.
"teach artificial intelligence systems how to conduct warfare."
Do you want Skynet?
Because that's how you get Skynet!
Sometimes the "writing on the wall" is blood spatter...
My initial reaction when I saw this news was that it was a boring choice. It's a step up from Galaga, so maybe it makes sense as a stepping stone, but as a game something like DOTA2 would be much more interesting.
DOTA2, unlike SC2, heavily depends on both cooperation AND competition between players as an integral part of the standard game. It's got all all the same fog-of-war issues (i.e imperfect knowledge). There's for all intents and purposes one map, so you can focus on the strategy of the game without the changing topology of the map interferring. There's also a huge library of replays to learn from, with more coming online every minute.
It'd be interesting to know if DOTA2 was considered and rejected for some reason. Maybe it's as easy as Valve not being open to providing the hooks they need, but that doesn't sound like Valve.
I guess the positives for SC2 is that it's simpler, and they won't have to contend with too many changes/new units since it's at the end of its life.
Belief is the currency of delusion.
I've always been a multiplayer man myself with just about two decades of history fighting people in Quake and StarCraft. While bots work reasonably well with single player games, multiplayer is a different matter. We're yet to be presented with a real AI in a game. They all cheat. My point is I will pay money to watch e-sports where AI and humans fight on equal terms and we have no idea who is going to win. and how. my money is on the korean pro
They are still going to lose to some Korean guy
A lot of Starcraft is how fast you can do things that don't require you to be particularly clever (clever is a large part of it, too, but time to execution is key, as is the ability to physically deal with multiple areas on the board). It seems very unfair if DeepMind can do things like see more of the board than its opponent's monitor and move/select faster than someone could with a keyboard and mouse.
Zergling rush kekeke.
Not sure how you can defend against an AI that can simultaneously and individually control 200 units. Kind of like the mutalisk and pathing in SC1, SC2 is broken in many ways where it's easy for an AI to win simply by brute force and having superhuman unit control. Even Koreans and other high level players make many mistakes in optimization and strategy and simply make up by being physically faster than their opponent.
Custom electronics and digital signage for your business: www.evcircuits.com
> DeepMind learned to beat the best go players in the world by teaching itself through trial and error.
AlphaGo was trained on databases of historical games. It looks for moves that are similar to what a human pro would play, and then reads out sequences to score the strength of the resulting position. It did not learn by itself from scratch. Once proficient, it was played against itself to improve.
They are addressing this directly, by limiting the APM of the AI to human levels. So it won't be able to rely on perfect micro to win.
So much for their commitment to integrity if they'll let a deep-pocketed botter buy them up.
Twitter supports and protects racists - by smearing their critics with the "Hate Speech" label.
What we have is Applied Intelligence and as far as the Artificial kind of AI that becomes a big philosophical debate. Even so, what is Intelligence? If you start to define it in a way where you can build upon it logically, you end up with obvious conclusions where for example, your house thermostat is intelligent.
The domain or context is essential to the consideration too. So, the house thermostat is intelligent and within it's tiny world it performs quite well adapting and making decisions with it's simple stimuli. It is easy for us humans to think since we can write describe that intelligence in code or as a math function that there is no intelligence, just mechanically defined cause/effect. It is arrogant to define intelligence in terms of capabilities of humans... or just some subset of humans; plus practically speaking, it constrains us to only a select few to be the judges. The thermostat will not perform intelligently playing chess; just as human experts out of their depth do not perform intelligently either.
So lets say we have some math that is powerful enough to describe the problem of winning at Jeopardy. Do you honestly think that we or any math genius will be able to fully grasp that solution? So then do we call that Intelligence? It's "mechanical" but it does a better job than our human solutions. But why is that not intelligence? Because it can be described in some way and copied between machines? (we can't do that with our expert Jeopardy players.) No.
Lets go to a common fall back position: Humans can teach themselves without as much help a broad range of tasks. We have teachers, books etc... but why should we consider that way of learning the only way? Again, we are constraining it to humans. So... how far from "Idiot Savant" do we have to get before we consider it Intelligent? Again still constraining it to humans... What about mentally limited humans, like children? Do we let them off the hook simply because they grow up?
Getting back to the "some math:" What if you could describe incredibly complex real world problems found in life as complex math approximations? Well, that is just what we have been doing and the whole process of finding those mathematical non-linear equations is beyond our intelligence but for some problems our brains somehow do approximate solutions (unless you can find a perfect chess player, etc.) The amazing thing is that the math derived from theories on how our brains work is how we have algorithms which find approximate solutions - these are described as complex non-linear approximations (far better than human descriptions.) It is an iterative discovery process akin to our learning. So you might again say that this math is mechanical... but as we keep getting closer to mirroring human approximation abilities or surpassing them doesn't the trend make you wonder if everything in life can be described mathematically? Humans can describe solutions as math for simple problems but the machines do the work quicker. Is it unfair if a human teacher helps describe the problems and types of math (approaches) needed to learn the best solution to the task? Is it unfair that you learned your alphabet in a linear order? as a song? So do we give up at the point where we have automated the teacher?
Perhaps life is a non-linear approximation of 42... Do we know what the question was? no. does it matter? probably not. But we live in the process of approximating it. ;-)
Democracy Now! - uncensored, anti-establishment news