|
On November 07 2016 19:32 Acrofales wrote:I think the BW vs. SC2 is mainly because there are already AI contests for BW, and the structure for building AI is already in place. However, I don't see any problem working on SC2. The DeepMind people might even have gone to Blizzard and suggested BW due to the available computational infrastructure, but Blizzard wants to push the game they are still making money with, and suggested they can open up a similar API for SC2. With the support of DeepMind (Google) and Blizzard, I don't doubt that a lot of the current AI development for BW will port their solutions to SC2, and the AI community for SC2 will get a major boost, because lets face it: for AI development it makes very little difference whether it's SC2 or BW (the major problems that need to be addressed are the same for both), but the direct support of Blizzard (and Google) for one will be a major push for that game. Or, just see it as dedgaem rancor flowing over into this thread 
Basically the argument here is that there is a PR advantage for Blizzard to push it from the SC2 side. That is also what I think it is, because for all intents and purposes the BW AI project is further along (though far, far from any feasible solution with current technology) and the technical argument would make BW be the better choice, easily.
This all makes me question the integrity of this as a project for AI from an academic perspective, and instead makes me feel like this is a "Google hotshots go after an even bigger leviathan than Go" PR stunt.
|
I can already taste the salt when alphasc's strategy starts with always choosing a specific race. 
|
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions.
|
On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions.
On your question: yes. Blizzard is making an API for DeepMind to use here. Specifically for this purpose.
On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way. This is because by choosing SC2, they are throwing out a lot of highly valuable and relevant progress towards a well-developed and mature, if horribly incomplete, project. And Google isn't some genius that can simply toss aside that much progress, "pave their own path," and expect it will somehow work out for the best. It's not true.
|
but the focus on SC2 makes is questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way.
Why? What else do you think DeepMind is looking to do?
|
On November 08 2016 02:27 LegalLord wrote:Show nested quote +On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. [...] they are throwing out a lot of highly valuable and relevant progress towards a well-developed and mature, if horribly incomplete, project.[...].
Yes it is incomplete. At the same time, after being involved in the community for (only) two months, I can pretty safely state the BW AI Bot community is currently at its peak, better than ever. And it will continue to go upwards. I will try hard myself to make my small contribution to make it more complete.
@Jett.Jack.Alvir: I did reply to your latest comment in the blog. Not sure if you are gonna be satisfied with the answer though
|
Well regardless whether they are or aren't pushing the boundaries of AI learning, I think doing SC2 will be more fun to watch.
Don't get me wrong, I love BW and watched it plenty of times, but I love SC2 more.
I see your point though, there is already so much progress with BW bots that choosing SC2 seems like an illogical choice.
edit: imp42, I read it and I am satisified. I really like your method of developing a bot. I feel like its capable of being ported into SC2 because of its simplistic approach. Keep up the awesome work!
|
On November 08 2016 02:54 beg wrote:Show nested quote +but the focus on SC2 makes is questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way. Why? What else do you think DeepMind is looking to do?
To be a PR stunt. To make the headlines look like: "Google is at it again! Geniuses who solved Go now move on to an even bigger leviathan: Starcraft!"
Google does some interesting research for sure, but ultimately it's a company that wants money. If Blizzard offered Google a sweetheart deal to push SC2 despite that being an academically foolhardy choice, then they will go with SC2. And that is what I think happened here.
|
On November 08 2016 02:27 LegalLord wrote:Show nested quote +On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way
On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that BW AI scene is now established? Can you provide solid reasons instead of what you believe is true?
I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team?
|
On November 08 2016 03:01 aQuaSC wrote:Show nested quote +On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that the scene is now established? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team?
I don't hate SC2 at all. I simply don't see their rationale, from an academic perspective, of actually doing SC2, precisely because they are throwing out years of progress by those who made AI before them. Among other things, there is a 24/7 AI test stream for BW and countless works by Berkeley and others, all done with BW.
DeepMind can make their own decisions, but I do not believe they are made from an academically wise perspective. They are basically retreading old ground for no academically justifiable reason.
|
On November 08 2016 03:06 LegalLord wrote:Show nested quote +On November 08 2016 03:01 aQuaSC wrote:On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that the scene is now established? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team? I don't hate SC2 at all. I simply don't see their rationale, from an academic perspective, of actually doing SC2, precisely because they are throwing out years of progress by those who made AI before them. Among other things, there is a 24/7 AI test stream for BW and countless works by Berkeley and others, all done with BW. DeepMind can make their own decisions, but I do not believe they are made from an academically wise perspective. They are basically retreading old ground for no academically justifiable reason.
I'd love to hear why is it wise to make the research behind each choice of games, and it's weird to me to think that the progress made in BW has to be largely scrapped and can't be moved over to a game of the same genre, but which has more complex and challenging choices on the example of macro mechanics which BW doesn't have, BW macro mechanic is ordering newly trained workers to mine which is not choice-based but mechanically demanding.
I can't understand how changing the game but staying within the same genre is "throwing out years of progress" in other thing than maybe parts of the code alone.
|
On November 08 2016 03:14 aQuaSC wrote:Show nested quote +On November 08 2016 03:06 LegalLord wrote:On November 08 2016 03:01 aQuaSC wrote:On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that the scene is now established? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team? I don't hate SC2 at all. I simply don't see their rationale, from an academic perspective, of actually doing SC2, precisely because they are throwing out years of progress by those who made AI before them. Among other things, there is a 24/7 AI test stream for BW and countless works by Berkeley and others, all done with BW. DeepMind can make their own decisions, but I do not believe they are made from an academically wise perspective. They are basically retreading old ground for no academically justifiable reason. I'd love to hear why is it wise to make the research behind each choice of games, and it's weird to me to think that the progress made in BW has to be largely scrapped and can't be moved over to a game of the same genre, but which has more complex and challenging choices on the example of macro mechanics which BW doesn't have, BW macro mechanic is ordering newly trained workers to mine which is not choice-based but mechanically demanding. I can't understand how changing the game but staying within the same genre is "throwing out years of progress" in other thing than maybe code alone.
From an AI perspective, SC2 and BW are basically the same problem. If they "solve" one then it's a practical task of solving the other, not a research task. The problem of real-time decision making in an environment that many think approximates a general intelligence decision problem is far more daunting than training stuff on a new game.
What they throw out is substantial. The code, as you mentioned, is one of those things - and that is far from trivial (companies have been destroyed by the decision to rewrite their code from scratch while throwing out all their legacy code). The second is expertise - they lose the ability to benefit fully from hiring BW people who are BW experts who have worked on BW for years. And the third and related topic is community. They lose all the collaborators they have who have worked on BW for this long because while the approach is the same, they stunt their ability to collaborate when they aren't even playing the same game. And I suppose fourth is availability - access to BW copies is much easier than access to SC2 copies, which makes it easier to collaborate with people who are conscious about spending money on lots of copies of SC2.
It just doesn't make sense. Not as an academic endeavor anyways. I think Blizzard just gave them a sweetheart deal to promote a newer game, and that's a losing strategy if they want real academic results.
|
Bisutopia19340 Posts
Using DeepMind on SC2 over SC1 is super exciting. SC1 has had 2 decades of learning and discovery. It'd be great to see what a powerful AI can do with an RTS that is still in its infancy. So many new discoveries for pro players can come from this. The only reason for SC1 to have deep mind is so that the AI will have a true challenger. Like in Go, you would want the AI to play the best possible opponent and this case the AI could play versus Flash (I'd include Bisu, but clearly the AI would be too intimidated by his looks to concentrate)..
|
On November 08 2016 03:22 LegalLord wrote:Show nested quote +On November 08 2016 03:14 aQuaSC wrote:On November 08 2016 03:06 LegalLord wrote:On November 08 2016 03:01 aQuaSC wrote:On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that the scene is now established? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team? I don't hate SC2 at all. I simply don't see their rationale, from an academic perspective, of actually doing SC2, precisely because they are throwing out years of progress by those who made AI before them. Among other things, there is a 24/7 AI test stream for BW and countless works by Berkeley and others, all done with BW. DeepMind can make their own decisions, but I do not believe they are made from an academically wise perspective. They are basically retreading old ground for no academically justifiable reason. I'd love to hear why is it wise to make the research behind each choice of games, and it's weird to me to think that the progress made in BW has to be largely scrapped and can't be moved over to a game of the same genre, but which has more complex and challenging choices on the example of macro mechanics which BW doesn't have, BW macro mechanic is ordering newly trained workers to mine which is not choice-based but mechanically demanding. I can't understand how changing the game but staying within the same genre is "throwing out years of progress" in other thing than maybe code alone. And I suppose fourth is availability - access to BW copies is much easier than access to SC2 copies, which makes it easier to collaborate with people who are conscious about spending money on lots of copies of SC2.
This is a missed argument since starter edition provides all the potential AI research needs. You just don't need to buy the full game and the API will be free and made - as they said - accessible to variety of people, not just academic researchers so the interest in potential research (or the game itself by the way) may rise among many people.
I completely disagree with your opinion that they made the deal to promote SC2 first.
|
On November 08 2016 03:01 aQuaSC wrote:Show nested quote +On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that BW AI scene is now established? Can you provide solid reasons instead of what you believe is true? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team?
I think I can give you plenty reasons:
- BW is much more stable. Who knows if Blizzard is going to release a new patch. Optimistically you could say that's the challenge that Deepmind wants. Realistically you have to admit it if they really want to deal with changing rules it would be much better for them to have those rules under their own control (by e.g. tweaking units in a map editor) without having any conflict of interest created by the fact Blizzard also has to support an active player base.
- Guess which program is going to be more light-weight to execute. A program developed in 1998, runnable on Windows98, or Sc2? There already exists a "headless" version of BW (no graphics) and you can easily create pretty much any API you want.
- compared to Sc2 BW is simpler in terms of possible moves, but arguably* deeper strategically. If you're really interested in "real" AI you would want to strip any unnecessary complexity and focus on the core issue.
- BW has a low resolution, making the jump from Atari games more reasonable if you want to go the pixel interpretation way.
- As has been said before, there is already research available on BW. The statement at the Blizzard panel that "all BW bots are scripted" is not a 100% true. Approaches using Neural Nets have been explored as well.
* arguably deeper: my personal opinion, no need to discuss it. If anybody thinks otherwise that's fine with me
|
On November 08 2016 03:27 aQuaSC wrote:Show nested quote +On November 08 2016 03:22 LegalLord wrote:On November 08 2016 03:14 aQuaSC wrote:On November 08 2016 03:06 LegalLord wrote:On November 08 2016 03:01 aQuaSC wrote:On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that the scene is now established? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team? I don't hate SC2 at all. I simply don't see their rationale, from an academic perspective, of actually doing SC2, precisely because they are throwing out years of progress by those who made AI before them. Among other things, there is a 24/7 AI test stream for BW and countless works by Berkeley and others, all done with BW. DeepMind can make their own decisions, but I do not believe they are made from an academically wise perspective. They are basically retreading old ground for no academically justifiable reason. I'd love to hear why is it wise to make the research behind each choice of games, and it's weird to me to think that the progress made in BW has to be largely scrapped and can't be moved over to a game of the same genre, but which has more complex and challenging choices on the example of macro mechanics which BW doesn't have, BW macro mechanic is ordering newly trained workers to mine which is not choice-based but mechanically demanding. I can't understand how changing the game but staying within the same genre is "throwing out years of progress" in other thing than maybe code alone. And I suppose fourth is availability - access to BW copies is much easier than access to SC2 copies, which makes it easier to collaborate with people who are conscious about spending money on lots of copies of SC2. This is a missed argument since starter edition provides all the potential AI research needs. You just don't need to buy the full game and the API will be free and made - as they said - accessible to variety of people, not just academic researchers so the interest in potential research (or the game itself by the way) may rise among many people. I completely disagree with your opinion that they made the deal to promote SC2 first.
One may think that people doing research would want access to multiplayer since playing ladder games is a perfectly valid approach to training your AI.
It's not an insurmountable issue, but it's just not one that BW has. It's a game easily available for free.
|
On November 08 2016 03:28 imp42 wrote:Show nested quote +On November 08 2016 03:01 aQuaSC wrote:On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that BW AI scene is now established? Can you provide solid reasons instead of what you believe is true? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team? I think I can give you plenty reasons: - BW is much more stable. Who knows if Blizzard is going to release a new patch. Optimistically you could say that's the challenge that Deepmind wants. Realistically you have to admit it if they really want to deal with changing rules it would be much better for them to have those rules under their own control (by e.g. tweaking units in a map editor) without having any conflict of interest created by the fact Blizzard also has to support an active player base.
They said their goal with SC2 from now on is to not make any big changes and let the game grow on itself, with potential tweaks being just numbers, not big changes.
- Guess which program is going to be more light-weight to execute. A program developed in 1998, runnable on Windows98, or Sc2? There already exists a "headless" version of BW (no graphics) and you can easily create pretty much any API you want.
Valid reason behind BW, they still may do something about it for SC2 in the future though.
- compared to Sc2 BW is simpler in terms of possible moves, but arguably* deeper strategically. If you're really interested in "real" AI you would want to strip any unnecessary complexity and focus on the core issue.
I personally disagree since we do not know how the AI is going to evolve and how the game may be played differently when it may find more optimal way of playing than is considered a current highest level, but I didn't play BW much so I won't delve into discussion on comparing both games.
- BW has a low resolution, making the jump from Atari games more reasonable if you want to go the pixel interpretation way.
I personally think it may be a challenge for making the AI to more efficiently interpret visual cues and such on higher resolutions.
- As has been said before, there is already research available on BW. The statement at the Blizzard panel that "all BW bots are scripted" is not a 100% true. Approaches using Neural Nets have been explored as well.
* arguably deeper: my personal opinion, no need to discuss it. If anybody thinks otherwise that's fine with me
I won't argue on that since I've never been into AI research in BW more than an interesting thing to look at and think about.
|
On November 08 2016 02:27 LegalLord wrote:Show nested quote +On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your question: yes. Blizzard is making an API for DeepMind to use here. Specifically for this purpose. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way. This is because by choosing SC2, they are throwing out a lot of highly valuable and relevant progress towards a well-developed and mature, if horribly incomplete, project. And Google isn't some genius that can simply toss aside that much progress, "pave their own path," and expect it will somehow work out for the best. It's not true.
I kinda disagree that they are throwing it out. If it's interesting algorithms, they can pretty easily be assimilated. It shouldn't take much work to make learning algorithms designed for the BW API to work on the SC2 API (assuming Blizzard makes a decent SC2 API). If it's the work that has been done on perfect muta control bots, then I disagree with the premise, because that is not very interesting from a research point of view anyway (although it's pretty impressive from a mechanical perspective
|
On November 08 2016 03:32 LegalLord wrote:Show nested quote +On November 08 2016 03:27 aQuaSC wrote:On November 08 2016 03:22 LegalLord wrote:On November 08 2016 03:14 aQuaSC wrote:On November 08 2016 03:06 LegalLord wrote:On November 08 2016 03:01 aQuaSC wrote:On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way On the other hand you may just hate Blizzard too much, why BW is better than SC2 for potential AI? Just because of the fact that the scene is now established? I think people at Deepmind are much more qualified to make such assumptions or comparisons, if they really thought BW would be better for it they would do it in BW. Or maybe evil Mike bought Google and their Deepmind team? I don't hate SC2 at all. I simply don't see their rationale, from an academic perspective, of actually doing SC2, precisely because they are throwing out years of progress by those who made AI before them. Among other things, there is a 24/7 AI test stream for BW and countless works by Berkeley and others, all done with BW. DeepMind can make their own decisions, but I do not believe they are made from an academically wise perspective. They are basically retreading old ground for no academically justifiable reason. I'd love to hear why is it wise to make the research behind each choice of games, and it's weird to me to think that the progress made in BW has to be largely scrapped and can't be moved over to a game of the same genre, but which has more complex and challenging choices on the example of macro mechanics which BW doesn't have, BW macro mechanic is ordering newly trained workers to mine which is not choice-based but mechanically demanding. I can't understand how changing the game but staying within the same genre is "throwing out years of progress" in other thing than maybe code alone. And I suppose fourth is availability - access to BW copies is much easier than access to SC2 copies, which makes it easier to collaborate with people who are conscious about spending money on lots of copies of SC2. This is a missed argument since starter edition provides all the potential AI research needs. You just don't need to buy the full game and the API will be free and made - as they said - accessible to variety of people, not just academic researchers so the interest in potential research (or the game itself by the way) may rise among many people. I completely disagree with your opinion that they made the deal to promote SC2 first. One may think that people doing research would want access to multiplayer since playing ladder games is a perfectly valid approach to training your AI. It's not an insurmountable issue, but it's just not one that BW has. It's a game easily available for free.
They said they will never let the API to be used on ladder, but focus more on letting it interpret replays gathered from actual ladder games played by people and go from there.
|
On November 08 2016 03:40 Acrofales wrote:Show nested quote +On November 08 2016 02:27 LegalLord wrote:On November 08 2016 02:22 Jett.Jack.Alvir wrote:
Well this would be a huge PR stunt for both Blizzard and Google. SC2 would get huge coverage, look at Go, and Google would push the boundaries of AI learning.
So Blizzard is allowing DeepMind to access SC2 api? I thought that DeepMind was looking at BW because there is no api restrictions. On your question: yes. Blizzard is making an API for DeepMind to use here. Specifically for this purpose. On your earlier statement: it's a PR stunt, yes, but the focus on SC2 makes it questionable whether or not they are really looking to "push the boundaries of AI learning" in any appreciable way. This is because by choosing SC2, they are throwing out a lot of highly valuable and relevant progress towards a well-developed and mature, if horribly incomplete, project. And Google isn't some genius that can simply toss aside that much progress, "pave their own path," and expect it will somehow work out for the best. It's not true. I kinda disagree that they are throwing it out. If it's interesting algorithms, they can pretty easily be assimilated. It shouldn't take much work to make learning algorithms designed for the BW API to work on the SC2 API (assuming Blizzard makes a decent SC2 API). If it's the work that has been done on perfect muta control bots, then I disagree with the premise, because that is not very interesting from a research point of view anyway (although it's pretty impressive from a mechanical perspective
Algorithms are primarily mathematical, so they would be able to use those with some primarily practical tweaking. The codebase already made, and the BW AI community to collaborate with, that is lost by going to SC2.
|
|
|
|
|
|
EPT
