Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI at the Dota 2 World Championships

openai.com

Post reply on HN
Print view View original

121–130 of 219 posts

Re: OpenAI at the Dota 2 World Championships

#121

Post by electrograv »

flunhat wrote: post #119
electrograv wrote: post #111

Earlier quoted context omitted.

Without even getting into misconceptions and inaccuracies here, the following quotes illustrate "the moving goalposts of AI": The almost-metaphysical "mystique" that many attribute (perhaps subconsciously) to human intelligence vs machine intelligence: > AI techniques, which are good at learning what is "in the data" but have not yet been shown to be capable of thinking outside the box > AIs would be highly vulnerabl…

I will consider an A.I. truly intelligent when it passes the Turing test with flying colors. And as a native English speaker, too (not just barely passing by posing as a 13 year old Ukrainian boy with a poor grasp of English, which is what happened last time). As far I know, no A.I. developed has ever met this bar. It seems that the nuances, inconsistencies, and total freedom of language make it a totally different k…

Again, you're moving the goalposts forward whenever AI surpasses them. This time you move the goalposts forward by requiring a proof of native English proficiency. Next time it will be something else; that goalpost will be achieved, and when it is, you will move the goalpost forward yet again.

Perhaps you'll require the Turing+++ test be conducted with audio rather than text. Then it will be video. Then a physical android. Then it will need to prove itself better than the human in an IQ test. Then it will need to pass various real world success tests, because IQ tests are too synthetic. But those won't be good enough either, so it will have to live 80+ years as a human in the real world without being discovered. But that's not enough, because maybe its life was too easy -- the real human experience is characterized by pain and suffering as well as joy, so we'll also need it to somehow prove its experience is more real. And on and on and on. It's always something else -- with every step forward, the success will be dismissed and the goalpost will move forward.

I should say this isn't intrinsically a bad thing, since it pushes us to advance the field of AI more and more. But IMO this is too often promoted as a pessimistic criticism of the AI field, rather than an encouraging push of optimism.

Why must this notion of binary "true intelligence" exist, anyway? Can't we see that intelligence is a spectrum (most likely with multiple dimensions of proficiency), and AI is continuously advancing upwards?

Re: OpenAI at the Dota 2 World Championships

#122

Post by justicezyx »

BLanen wrote: post #30
justicezyx wrote: post #8

Earlier quoted context omitted.

OK it's happening right now, I saw machine the host's announcement

Weird website... No indication that a match is happening/happened/ or going to happen or with times or not. I guess I missed it and the stream link is now just a general link to the TI stream, which confused me for a bit.

They probably dont expect the dota tournament to have such a large influence scope...

Re: OpenAI at the Dota 2 World Championships

#123

Post by sondr3 »

DannyDaemonic wrote: post #75
habitue wrote: post #59

So an interesting thing you could do as a game company with an "unbeatable" bot is to use it to balance a metagame. Let the bots all play each other and tweak character stats etc until they win a proportional amount of the time. (This presupposes that the bot learns the game the way OpenAI claims it is, without needing to learn from player replays or from playing in a very different way than human players do with tre…

I think balance is a bigger problem than people realize. It's much harder than you'd think, and the most common way of balancing things is to simply make them more "samey". I was part of the Warcraft 3 beta. When it started all the races felt so unique. It's a bit foggy now but I think, for example, all the elves buildings - which appeared tree like - would automatically regenerate. Once they started balancing the ga…

This is luckily a problem Dota2 doesn't suffer from, we've been incredibly lucky to have Icefrog be the main force behind it for over a decade. It's an incredibly well balanced game, at this International (World Championships for Dota2) 112 of 113 heroes has been picked and/or banned. The amount of diversity you have in strategy is amazing, there is a meta obviously, but teams have very individual styles and heroes they prioritize.

As far as I'm concerned Dota2 is probably the most well balanced competitive video game out there.

Re: OpenAI at the Dota 2 World Championships

#124

Post by justicezyx »

ronald_raygun wrote: post #33
justicezyx wrote: post #20

To be clear 1v1 mid lane is harder than 1 unit v 1 unit in sc. But it is at least 3 levels behind 5v5 human play. So first it's laining, which is showing in the game. Then is the ganking basically 2-3 player working together. Above that that's 5 men team fight. Then you have the strategy planning in the band pick phase, and in game movement coordination. There are other things like item choices, in game communication…

I'm not sure about DOTA, but in LOL there is also champion select which happens before the game starts, where you try to pick/ban/steal champions to get a good team comp and get the other team to have a bad team comp. It's lots of know overall strategy, what your enemy likes, and some game theory. You can lose the game before your summoner even hits the field.

Put my war3 dota hat on... LoL is a simplified dota which are tailored to less-skilled players. The basic elements are all the same.

Re: OpenAI at the Dota 2 World Championships

#125

Post by sondr3 »

thefreeman wrote: post #74
ahh wrote: post #54

The developer interviewed claimed that there was no domain-specific knowledge and implied (though didn't explicitly state) there wasn't any training against non-OpenAI bots or players. (I'd love to know the reward function they used for whatever Q-learning variation they ran with.) If this is accurate, one of the things I'm most impressed with is that the bot figured out creep-blocking. (I can't find a good GIF, but…

I don't know that they specifically said there was no domain-specific knowledge. iirc they said they didn't "teach it the rules of dota" but they also said the training involved "coaching". I interpret that to include showing the bot useful techniques (like creep blocking) which the AI then learned leads to higher win rates, etc.

They also mentioned that in the beginning the bot figured out that the best way to win was to not play the game (aka hiding in it's own base). Then it started running around wildly, dying to enemy towers in the wrong lanes at the map. So it definitely took some nudging getting it to do something more than being AFK in base.

Re: OpenAI at the Dota 2 World Championships

#126

Post by nopinsight »

flunhat wrote: post #119
electrograv wrote: post #111

Earlier quoted context omitted.

Without even getting into misconceptions and inaccuracies here, the following quotes illustrate "the moving goalposts of AI": The almost-metaphysical "mystique" that many attribute (perhaps subconsciously) to human intelligence vs machine intelligence: > AI techniques, which are good at learning what is "in the data" but have not yet been shown to be capable of thinking outside the box > AIs would be highly vulnerabl…

I will consider an A.I. truly intelligent when it passes the Turing test with flying colors. And as a native English speaker, too (not just barely passing by posing as a 13 year old Ukrainian boy with a poor grasp of English, which is what happened last time). As far I know, no A.I. developed has ever met this bar. It seems that the nuances, inconsistencies, and total freedom of language make it a totally different k…

Will you consider a set of AIs based on the same underlying architecture that can perform several different online jobs as well as their human counterparts truly intelligent, without any reservations regardless of the approach used [1]?

This would include the ability to communicate with their human hirers and collaborators in natural language.

[1] We can also think of the human brain as a massive structure of relatively simple neurons with methods of communications among them that can be translated to mathematical parameters.

Re: OpenAI at the Dota 2 World Championships

#127

Post by gnufied »

thefreeman wrote: post #74
ahh wrote: post #54

The developer interviewed claimed that there was no domain-specific knowledge and implied (though didn't explicitly state) there wasn't any training against non-OpenAI bots or players. (I'd love to know the reward function they used for whatever Q-learning variation they ran with.) If this is accurate, one of the things I'm most impressed with is that the bot figured out creep-blocking. (I can't find a good GIF, but…

I don't know that they specifically said there was no domain-specific knowledge. iirc they said they didn't "teach it the rules of dota" but they also said the training involved "coaching". I interpret that to include showing the bot useful techniques (like creep blocking) which the AI then learned leads to higher win rates, etc.

Not whole lot but some of this stuff can be seen in this video - https://www.youtube.com/watch?v=wpa5wyutpGc

I still can't quite tell if this behaviour was coached to the bot or it figured it out itself.

Re: OpenAI at the Dota 2 World Championships

#128

Post by perishabledave »

terda12 wrote: post #50

As a longtime DotA player and someone who's following the pro scene, this is very impressive. Especially considering how it's beaten Sumail, widely regarded as one of the best 1v1 players in the world. Can't wait to see what OpenAI have in store a year from now for 5v5.

Sumail won once until they gave the bot insane creep blocking skills.

https://twitter.com/Phillip_Aram/status/896162260455800832

Re: OpenAI at the Dota 2 World Championships

#129

Post by dvt »

jlebar wrote: post #100
dvt wrote: post #87

Saw this live and as someone that's played Dota for many years, it's not as impressive as people make it out to be. A Shadowfiend 1v1 is primarily a test of mechanical skill and not judgment. A similar comparison is if a Counter-Strike or Quake bot would instantly snap to your head getting a headshot. Like, yeah, cool I guess, and it would beat 100% of human players 100% of the time, but it's not even remotely as imp…

> but I think that it was one of those cases where it was "coached" (same as the creep blocking). What makes you think that? In the interview, they explicitly disclaim this.

In the interview, they literally said they coached it to have certain behaviors.

Re: OpenAI at the Dota 2 World Championships

#130

Post by flunhat »

electrograv wrote: post #121
flunhat wrote: post #119

Earlier quoted context omitted.

I will consider an A.I. truly intelligent when it passes the Turing test with flying colors. And as a native English speaker, too (not just barely passing by posing as a 13 year old Ukrainian boy with a poor grasp of English, which is what happened last time). As far I know, no A.I. developed has ever met this bar. It seems that the nuances, inconsistencies, and total freedom of language make it a totally different k…

Again, you're moving the goalposts forward whenever AI surpasses them . This time you move the goalposts forward by requiring a proof of native English proficiency. Next time it will be something else; that goalpost will be achieved, and when it is, you will move the goalpost forward yet again. Perhaps you'll require the Turing+++ test be conducted with audio rather than text. Then it will be video. Then a physical a…

The Turing test is hardly a new measure - it's been around for ~70 years and hasn't been passed yet. But otherwise I agree with what you said - this is just my personal measure of when we'll be in society-shaking territory.
Post reply on HN