Read more.Skilled pro players eked out a single victory against the throttled APM and reaction time AI.
Read more.Skilled pro players eked out a single victory against the throttled APM and reaction time AI.
this is pretty scary honestly. I remember not too long ago when they managed chess, the advancement is going fast. The scary bit is learning 200years worth of gaming stratergy in 10 days.
I love that they have included the Neural Network visual and its consideration trees. Really cool stuff!
Below is a video extracted from above which just shows a single game but shows the AlphaStars thought processes visually, really neat:
Pleiades (25-01-2019)
True, but the one the humans won was the match where the AI couldn't already see the entire map (fog of war on).
Agreed, but just like in Dota this is actually very good for human learning as well since we are learning from them and are learning ways to counter them now. (Also we are evolving our own strategies)
I don't think the AI will just be left undefeated eventually
I think we will always jump back.
Also if you think about it, you need an AI supercomputer to beat a human being after training for 200 years, where as the human player learns to manage complex problems 20x quicker. (at-least in Star Craft 2 and similarly for Dota 2)
Now considering the innate limitation of not being able to learn 200 years of training within a few days for a human being and also the limitation of reaction speeds where the AI definitely has an advantage over humans.
Still the inherent weakness of taking very long to master complex problems even when done at hyper speeds will give the human an advantage in adaptability, at-least for now especially if meta's(game rules) get's changed on the fly.
For example if we are talking dota now then I would say we need to get Human's and the AI to train on a certain game version for months and then just before they play the game we change the rules of the game.
In this case the AI would probably break or at-least give the advantage to the humans.
I know this sounds counter intuitive, but this is real life and if the AI are being trained to face everyday challenges that we as human's face then they will need to know that the rules of the game is not a constant and can be changed at any time.
I would love to see a Dota match against AI and human's set up like this so that even with all of the training you have done, that on the day of the game a lot of it may need to be thrown out.
OpenAI did mention they were preparing a 5-player AI bot team to take on Dota pros a while back, after generally dismantling the 1v1 mid matchup mode. They've been slowly introducing more parts of the game to the bots; wards, buybacks, more heroes into the "understood" pool, etc. Would be surprised if TI9 or TI10 / TIX did not have a 5v5 with the winner of the tournament. OpenAI also said, though, that the resources they apply to Dota would diminish now that they've effectively delivered their proof of concept and gotten the team up to speed on training AI, that it was fun but not really their priority (obviously..)
Impressed especially by the fact that they throttled the APM and response time.
I can kind of see how AI could be unbeatable in certain genres like fighting games just by being able to accurately respond to each frame rate and never miss any key, but a complex RTS is something else all together.
Makes me wonder just how far AI will eventually evolve.
my washing machine is already more intelligent than me- this is how it hides the odd socks where i am unable to find them. and then puts them back again just after i give up looking :/
bastard
Well, they're already getting AI to drive my car instead of me, and the department downstairs is already trialling AI-controlled survey kit that will do my job instead of me.... Why not have an AI that plays my computer games instead of me, too!!
I'd go off and be irrelevant in some corner somewhere, but I'm sure there's an AI that can do it instead of me.....
_______________________________________________________________________
Originally Posted by Mark Tyson
There are currently 1 users browsing this thread. (0 members and 1 guests)