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

More on Dota 2

blog.openai.com

Post reply on HN
Print view View original

91–100 of 106 posts

Re: More on Dota 2

#91

Post by graphitezepp »

velobro wrote: post #67
BaronSamedi wrote: post #34

Earlier quoted context omitted.

I completely disagree. An API is software's natural input mechanism just like the senses are a human's natural input mechanism. Having the AI use human senses unfairly handicaps it. More importantly, however, is that this is not the key problem. The key problem is teaching the AI strategy and tactics. What heroes to pick? Where to lane them? When to rotate? What items to buy? What spells to level up? What enemies to…

The Dota 2 bot is no different than Aimbots in FPS games. The bot was able to access the api to perfectly target the exact location and instantly cast a spell, much like an Aimbot can instantly get headshots.

It's a good comparison honestly. They stripped away all the complexity of dota to this one single scenario were the things bot's are naturally going to be good at (last hitting, precise distance evaluation) matter over strategy.

Re: More on Dota 2

#92

Post by kpil »

tictacttoe wrote: post #18
omarforgotpwd wrote: post #4

I’m by no means an expert, but I’m fascinated by the idea that a neural net playing against itself can substantially outperform a supervised learning approach with a large training data set. I mean, gathering training data and making sure it’s labeled correctly and all that is a huge hassle so if you could eliminate that step or even reduce the amount or quality of training data required that should be a big win for…

It's very cool, but I think it also requires a very specific "adversarial" problem with a well defined notion of success (winning the game). If your machine learning task is something more nuanced and harder to define, e.g. identify word synonyms, I don't see how you can get around having a training data set.

I played with evolving algorithms playing some kind of robot war (in java) almost 20 years ago, and beside the fact that you had to be veeery patient since evolving a generation took 10 minutes at best, I realized that it's very hard to create a survival criteria that matches your intention.

I e, most robots fled and hid in the corners. I added additional critiera for hitting enemies, and the robots fled while randomly shooting bullets and hid in the corners...

No epic fights.

Hmm. Maybe I have the code somewhere...

Re: More on Dota 2

#93

Post by autokad »

lvoudour wrote: post #15

I know it has been mentioned a lot the past few days, but since the articles keep flowing about it I'll mention it again: It's a great feat and kudos to the openai team, but it is VERY unfair for the human players who rely on a sensory interface vs a direct API connection. That's unlike chess or go where the interface isn't important. The really impressive feat will be an AI that uses the same sensory information to…

one thing AI bots can be good for is testing to see if games are balanced. For instance, I am a zerg player and I bought star craft 2, but it was immediately clear to me that the game was heavily unbalanced. I quit playing.

whether you agree protos was over-powered or not, I think we can all agree that game developers can benefit from AI with human limitations. it can help them design better games

Re: More on Dota 2

#94

Post by tahw »

The version they used for TI had a variety of rules that completely changed the metagame of 1v1 (no bottle, for example). Even ignoring the obvious API advantage, the match was unfair because the Pros had never trained under the constraints that the AI team brought.

Re: More on Dota 2

#95

Post by Twirrim »

damnfine wrote: post #49
gcp wrote: post #11

Earlier quoted context omitted.

It's a highly specific procedure that happens before there is interaction with the opponent, so without "handing over" the understanding that having creeps on your high-ground is good, it's very hard for the learning to see through the noise and discover this.

Exactly why this is not impressive to me. The point is to be able to learn the rules, but all I see is some of not only the rules, but the actions already prespecified in many cases. Yes its hard, and thats why humans still rule the roost.

Surely all this RL process did was speed up what the computer would have learned, by a large stretch? The "cost" factors they chose would have hit them ultimately, regardless of if the bot stood still in the base, or wandered off elsewhere.

Re: More on Dota 2

#96

Post by rasz »

BaronSamedi wrote: post #34
lvoudour wrote: post #15

I know it has been mentioned a lot the past few days, but since the articles keep flowing about it I'll mention it again: It's a great feat and kudos to the openai team, but it is VERY unfair for the human players who rely on a sensory interface vs a direct API connection. That's unlike chess or go where the interface isn't important. The really impressive feat will be an AI that uses the same sensory information to…

I completely disagree. An API is software's natural input mechanism just like the senses are a human's natural input mechanism. Having the AI use human senses unfairly handicaps it. More importantly, however, is that this is not the key problem. The key problem is teaching the AI strategy and tactics. What heroes to pick? Where to lane them? When to rotate? What items to buy? What spells to level up? What enemies to…

>What items to buy?

hardcoded by a pro dota 2 player hired as a consultant

Re: More on Dota 2

#97

Post by jdoliner »

tahw wrote: post #94

The version they used for TI had a variety of rules that completely changed the metagame of 1v1 (no bottle, for example). Even ignoring the obvious API advantage, the match was unfair because the Pros had never trained under the constraints that the AI team brought.

They played under standard 1v1 tournament rules: http://wiki.teamliquid.net/dota2/Dota_2_Asia_Championships/2...

Re: More on Dota 2

#98

Post by shopoholic »

"Arteezy also played a match against our 7.5k semi-pro tester. Arteezy was winning the whole game, but our tester still managed to surprise him with a strategy he’d learned from the bot. Arteezy remarked afterwards that this was a strategy that Paparazi had used against him once and was not commonly practiced."

Does anyone have a clue what this "strategy" that Paparazi used could be?

Re: More on Dota 2

#99

Post by misticdeveloper »

So it appears their bot isn't cheating with vision, and has its action speed capped to human levels. Interesting!

Sad they had whitelisted item builds. I thought the whole point of a machine learnign bot was it was supposed to learn these themselves.

5v5 full game is way more complex than Starcraft. Hope OpenAI are ready.

Re: More on Dota 2

#100

Post by aoeuasdf1 »

Twirrim wrote: post #95
damnfine wrote: post #49

Earlier quoted context omitted.

Exactly why this is not impressive to me. The point is to be able to learn the rules, but all I see is some of not only the rules, but the actions already prespecified in many cases. Yes its hard, and thats why humans still rule the roost.

Surely all this RL process did was speed up what the computer would have learned, by a large stretch? The "cost" factors they chose would have hit them ultimately, regardless of if the bot stood still in the base, or wandered off elsewhere.

Not necessarily - maybe a mixed strategy of

(1) Not creepblocking at all, and letting your opponent have your creeps under their tower

(2) Modest creepblocking to punish (1)

(3) Severe creepblocking to punish (2)

Would be better than some hand-trained RL creepblocking which is divorced from game outcomes.

Post reply on HN