21–30 of 321 posts
Earlier quoted context omitted.
I assume obtaining a decent-sized training dataset is gonna be a bloody business.
Isn't this trained via playing against itself? I don't think there's a dataset involved.
Earlier quoted context omitted.
I assume obtaining a decent-sized training dataset is gonna be a bloody business.
Isn't this trained via playing against itself? I don't think there's a dataset involved.
Earlier quoted context omitted.
I assume obtaining a decent-sized training dataset is gonna be a bloody business.
Isn't this trained via playing against itself? I don't think there's a dataset involved.
Even if you just consider self-play, I don't see how you would create a simulation that is realistic enough so that you could generalize afterwards to reality. RL today has an extremely hard time dealing with different distributions.
You can see the amount of work OpenAI [1] had to do to go from a virtual hand+rubik's cube to real ones, even though you can make a very accurate simulation much more easily.
Earlier quoted context omitted.
A bit further away I would say. So far it trains on a deterministic model by playing millions of games against itself. It can be thrown off by a single rule change. The challenge here in making an AI usable on the real battlefield is more on making a realistic simulation rather than on a better AI.
So, what I'm hearing here is that we should start a series of endless wars?
More seriously, most of the "intelligence" in AI agents are displayed during the training phase, after that you have a fixed black box that can respond well to already seen inputs and unpredictably to anything new. In effect the AI can interpolate but has no sense to guide extrapolation.
There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.
There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.
There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.
There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.
> After 50 games, however, DeepMind hit a snag. Some players had noticed that three user accounts on the Battle.net gaming platform had played the exact same number of StarCraft II games over a similar time frame — the three accounts that AlphaStar was secretly using. When watching replays of these matches, players noticed that the account owner was performing actions that would be extremely difficult, if not impossi…
I'm not sure this is unfairness. IIRC they put in a fair bit of effort to put it on a level playing field with humans by limiting APM and not allowing it to observe multiple areas simultaneously by spam moving the camera. It might have some minor unfair advantage in terms of being able to click with pixel perfect accuracy, but they're marginal and from watching this project evolve, it's pretty clear that the strategi…
> After 50 games, however, DeepMind hit a snag. Some players had noticed that three user accounts on the Battle.net gaming platform had played the exact same number of StarCraft II games over a similar time frame — the three accounts that AlphaStar was secretly using. When watching replays of these matches, players noticed that the account owner was performing actions that would be extremely difficult, if not impossi…
These extremely difficult/impossible things didn't really give an advantage. For example, AlphaStar would sometimes click on an object at the border of the screen. For humans that would be almost impossible, because the screen would scroll when the mouse approaches the border. Similarly, AlphaStar would not play with group hotkeys, but use a different technique. However, in none of the analyses, people noticed things…
That humans cannot reliably perform these actions because of the limitations of our corporeal form means that Alphastar has an advantage over a human player. Limiting APM isn't enough.