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

OpenAI bots competing against Humans right now

twitch.tv

Post reply on HN
Print view View original

71–80 of 138 posts

Re: OpenAI bots competing against Humans right now

#71

Post by asdfasgasdgasdg »

douglaswlance wrote: post #69
21 wrote: post #49

Earlier quoted context omitted.

The next AI will always be much better (see AlphaGo progression). Humans, not so much, as in all top-level competitions, human abilities improve minimally at the top, because we have millions of humans competing against each other until the plateau of human performance is reached. Then you can push that a bit more with drugs (see doping in sports). And after that, you are pretty much done. So it's only a matter of ti…

Humans tend to progress by learning from each other. The AI will teach us.

Whether the AI teaches us or not, once it surpasses us, we will not catch up. This is the case for every game AI that has ever surpassed human performance so far, and there's no reason to expect that this will be different in the case of DotA.

Re: OpenAI bots competing against Humans right now

#72

Post by fizx »

halflings wrote: post #35
kenning wrote: post #23

Earlier quoted context omitted.

dota 2 is not as extreme about this as, say, starcraft. in starcraft, most "strategies" are heavily scripted build orders that almost never deviate from a handful of openings (similar to opening moves in chess) and a large amount of winning comes from the ability to quickly give orders to your troops ("micro"). This is an example of a strategy that is not viable without superhuman reactions: https://www.youtube.com/w…

> in starcraft, most "strategies" are heavily scripted build orders that almost never deviate from a handful of openings (similar to opening moves in chess) and a large amount of winning comes from the ability to quickly give orders to your troops ("micro") As somebody who plays StarCraft casually (gold/low plat in ladder), this is not true. It's even less true for pro players. The level of strategy in StarCraft is i…

I wonder how far you'd get with a bot that macros perfectly but also A-moves 2-3 groups.

Re: OpenAI bots competing against Humans right now

#73

Post by andrei_says_ »

stale2002 wrote: post #57
darepublic wrote: post #50

Earlier quoted context omitted.

I agree that AIs will eventually win. But I only consider human beings beaten when the AI is interfacing with the machine the same way as humans -- looking at the monitor, and inputting commands through keyboard and mouse. That is on a different level than just hooking into a log of events and calculating your next move. Given enough time humans would do that better than the AI imo

I mean, interacting with the mouse and keyboard isn't the interesting part. Like, imagine if this was a chess AI, and we were trying to determine who was better at chess, humans or AI. Would you make the AI use robotic hands to move the pieces? No, because thats not the interesting part of chess. The interesting part of chess is the strategy.

Interacting with the mouse and keyboard at this speed and precision is absolutely a very interesting part for me. It is a limitation of he human organism.

What if we could pit humans and ai bots at the speed of human imagination?

Re: OpenAI bots competing against Humans right now

#74

Post by king07828 »

stale2002 wrote: post #57
darepublic wrote: post #50

Earlier quoted context omitted.

I agree that AIs will eventually win. But I only consider human beings beaten when the AI is interfacing with the machine the same way as humans -- looking at the monitor, and inputting commands through keyboard and mouse. That is on a different level than just hooking into a log of events and calculating your next move. Given enough time humans would do that better than the AI imo

I mean, interacting with the mouse and keyboard isn't the interesting part. Like, imagine if this was a chess AI, and we were trying to determine who was better at chess, humans or AI. Would you make the AI use robotic hands to move the pieces? No, because thats not the interesting part of chess. The interesting part of chess is the strategy.

Agreed that the strategy is an interesting part.

Another interesting part will be creating an AI / neural network that can utilize inputs that are closer to human level inputs (e.g., using the frame buffer and audio out as input to the neural network and passing the outputs of the neural network to a keyboard and mouse driver). Just let the network train itself without having a human laboriously determine the topology of the neural network. Such a neural network can then be applied to several different types of games / problems much more quickly than at present where significant human labor is required to generate deeply customized neural networks for each game / problem.

Re: OpenAI bots competing against Humans right now

#75

Post by make3 »

ufo wrote: post #56

In the last game of the series the bots were forced to play an intentionally terrible hero lineup. The humans finally got to win a game but more interesting for me was that the times when the AI did seemingly crazy things were much more common. I wonder if this is an artifact of the training methodology: maybe if your team is very weak then your choices are also weaker, and reinforcement learning doesn't work as well…

maybe the team never picked lineup it knew were bad, and as such never trained with them

Re: OpenAI bots competing against Humans right now

#77

Post by ethbro »

asdfasgasdgasdg wrote: post #71
douglaswlance wrote: post #69

Earlier quoted context omitted.

Humans tend to progress by learning from each other. The AI will teach us.

Whether the AI teaches us or not, once it surpasses us, we will not catch up. This is the case for every game AI that has ever surpassed human performance so far, and there's no reason to expect that this will be different in the case of DotA.

> game AI that has ever surpassed human performance so far

Am I missing something, or does that set consist of Checkers, Chess, and Go so far? (presumably with analogous misc games of comparable complexity)

Discounting the reaction time wins, I'd say the sample size is too limited to generalize to eventual AI behavior in more complex / open-ended games.

Extrapolation was the cause of the last AI winter.

Re: OpenAI bots competing against Humans right now

#78

Post by gsich »

21 wrote: post #51
darepublic wrote: post #50

Earlier quoted context omitted.

I agree that AIs will eventually win. But I only consider human beings beaten when the AI is interfacing with the machine the same way as humans -- looking at the monitor, and inputting commands through keyboard and mouse. That is on a different level than just hooking into a log of events and calculating your next move. Given enough time humans would do that better than the AI imo

Come on, do you think hooking a robot to the keyboard is the hard part? Do you want 5 fingers too? And if watching the screen, do you want it to have bad eyes like we do too (good resolution only in the center)?

Yes. Right now the AI has more information than the humans.

Re: OpenAI bots competing against Humans right now

#79

Post by rhaps0dy »

king07828 wrote: post #74
stale2002 wrote: post #57

Earlier quoted context omitted.

I mean, interacting with the mouse and keyboard isn't the interesting part. Like, imagine if this was a chess AI, and we were trying to determine who was better at chess, humans or AI. Would you make the AI use robotic hands to move the pieces? No, because thats not the interesting part of chess. The interesting part of chess is the strategy.

Agreed that the strategy is an interesting part. Another interesting part will be creating an AI / neural network that can utilize inputs that are closer to human level inputs (e.g., using the frame buffer and audio out as input to the neural network and passing the outputs of the neural network to a keyboard and mouse driver). Just let the network train itself without having a human laboriously determine the topolog…

>Just let the network train itself without having a human laboriously determine the topology of the neural network

I hope this little koan illustrates that this sentence is impossible to execute. The human always has to specify something.

--

In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6.

"What are you doing?", asked Minsky.

"I am training a randomly wired neural net to play Tic-tac-toe", Sussman replied.

"Why is the net wired randomly?", asked Minsky.

"I do not want it to have any preconceptions of how to play", Sussman said.

Minsky then shut his eyes.

"Why do you close your eyes?" Sussman asked his teacher.

"So that the room will be empty."

At that moment, Sussman was enlightened.

Re: OpenAI bots competing against Humans right now

#80

Post by tialaramex »

ethbro wrote: post #77
asdfasgasdgasdg wrote: post #71

Earlier quoted context omitted.

Whether the AI teaches us or not, once it surpasses us, we will not catch up. This is the case for every game AI that has ever surpassed human performance so far, and there's no reason to expect that this will be different in the case of DotA.

> game AI that has ever surpassed human performance so far Am I missing something, or does that set consist of Checkers, Chess, and Go so far? (presumably with analogous misc games of comparable complexity) Discounting the reaction time wins, I'd say the sample size is too limited to generalize to eventual AI behavior in more complex / open-ended games. Extrapolation was the cause of the last AI winter.

Poker. Although Heads Up Limit Texas Hold 'Em has been essentially solved the No Limit variant (in which you actually decide how much to bet) is very far from solved. An AI beat the best players in the world anyway. It plays crazy, but it plays crazy in a way they weren't able to exploit at all. Doug Polk (also one of the best in the world in this narrow specialty) did some funny videos but the humans got crushed.

So that's a pretty different game, it's got a big luck factor and has asymmetrical information and still the AI just kept getting better and the humans... didn't

Post reply on HN