Grandmaster level in StarCraft II using multi-agent reinforcement learning
1–10 of 321 posts
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#2I hope they don't stop here without doing a world champion challenge. It looks like they're still significantly below professional player strength.
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#3> placing within the top 0.15% of the region's 90,000 players
> 61 wins out of 90 games against high-ranking players
This doesn't seem to be quite as commanding as it was in Go. Do we know what MMR it reached or if it consistently beat players like Serral?
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#4How soon is this put into the hands of battlefield commanders? Not presuming it’s a bad thing, but I wonder when we’ll hear the outcome of a battle was aided by this kind of intelligence.
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#5> 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 impossible, for a human. In response, DeepMind began using a number of tricks to keep the trial blind and stop players spotting AlphaStar, such as switching accounts regularly.
So instead of fixing the unfairness... they tried to hide it?
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#6> placing within the top 0.15% of the region's 90,000 players > 61 wins out of 90 games against high-ranking players This doesn't seem to be quite as commanding as it was in Go. Do we know what MMR it reached or if it consistently beat players like Serral?
It hasn't beat Serral once, from the article: "The AI wasn’t able to beat the best player in the world".
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#7How soon is this put into the hands of battlefield commanders? Not presuming it’s a bad thing, but I wonder when we’ll hear the outcome of a battle was aided by this kind of intelligence.
I assume obtaining a decent-sized training dataset is gonna be a bloody business.
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#8How soon is this put into the hands of battlefield commanders? Not presuming it’s a bad thing, but I wonder when we’ll hear the outcome of a battle was aided by this kind of intelligence.
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.
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#9How soon is this put into the hands of battlefield commanders? Not presuming it’s a bad thing, but I wonder when we’ll hear the outcome of a battle was aided by this kind of intelligence.
I assume obtaining a decent-sized training dataset is gonna be a bloody business.
for starters you just need a gps antenna on each soldier, an ammo count and a health meter (healthy, hit, safe).
these 3 pieces of info already allow you to create a strategy framework
Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning
#10How soon is this put into the hands of battlefield commanders? Not presuming it’s a bad thing, but I wonder when we’ll hear the outcome of a battle was aided by this kind of intelligence.
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.