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

DeepMind and Blizzard Open StarCraft II as an AI Research Environment

deepmind.com

Post reply on HN
Print view View original

71–80 of 283 posts

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#71

Post by qub1t »

A lot of people here seem to be underestimating the difficulty of this problem. There are several incorrect comments saying that in SC1 AIs have already been able to beat professionals - right now they are nowhere near that level.

Go is a discrete game where the game state is 100% known at all times. Starcraft is a continuous game and the game state is not 100% known at any given time.

This alone makes it a much harder problem than go. Not to mention that the game itself is more complex, in the sense that go, despite being a very hard game for humans to master, is composed of a few very simple and well defined rules. Starcraft is much more open-ended, has many more rules, and as a result its much harder to build a representation of game state that is conducive to effective deep learning.

I do think that eventually we will get an AI that can beat humans, but it will be a non-trivial problem to solve, and it may take some time to get there. I think a big component is not really machine learning but more related to how to represent state at any given time, which will necessarily involve a lot of human-tweaking of distilling down what really are the important things that influence winning.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#72

Post by mortehu »

infinite8s wrote: post #56
tantalor wrote: post #54

Earlier quoted context omitted.

Watson’s hand looks like a clear, Plexiglas, cylindrical soda can with a few metal screws in the top and a wire extending from the bottom that is connected to Watson’s Front-End Controller. The mechanical hand wraps around the Jeopardy! buzzer which is inserted in the bottom of the Plexiglas cylinder and is held in place by a clamp. Watson’s hand uses a solenoid to physically press the same button that the humans mus…

Typical human response time to a stimulus is about 200ms. That of course doesn't factor in the decision time, but once the brain decides on an action it takes about 200 Ms for the signal to propagate to the relevant muscles.

https://www.humanbenchmark.com/tests/reactiontime seems to agree with you. The median there is 215ms, which probably includes some unmeasurable rendering and input latency.

In Jeopardy, though, people can anticipate the moment the buzzer becomes active.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#73

Post by SiempreZeus »

It's a bit too bad they're having to move towards supervised learning and imitation learning.

I totally understand why they need to do that given the insane decision trees, but I was really hoping to see what the AI would learn to do without any human example, simply because it would be inhuman and interesting.

I'm really interested in particular if an unsupervised AI would use very strange building placements and permanently moving ungrouped units.

One thing that struck me in the video was the really actively weird mining techniques in one clip and then another clip where it blocked its mineral line with 3 raised depots...

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#74

Post by indescions_2017 »

JefeChulo wrote: post #30

"so agents must interact with the game within limits of human dexterity in terms of “Actions Per Minute”." I am really glad they are limiting APM because otherwise things just get stupid.

OOTH, altering the source to remove any human dexterity limits and watching subsequent AI vs AI battles play out at 60fps would be really fun to spectate ;)

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#76

Post by cjbprime »

sidusknight wrote: post #34
keerthiko wrote: post #33

Earlier quoted context omitted.

Are you sure you're interpreting 'macro' correctly? 'Macro' in the context of RTS games isn't the same as 'macro commands' in scripting, but refers to basically all high level decisions. RTS is divided up into Macro, tactics and micro: - Macro: resource prioritization (army vs expansions vs upgrades), scouting to understand the opponent's macro choices, choosing the right posture in response (defensive, harassment or…

Your definition of macro is a lot more encompassing than how I see it used in SC2. It normally refers to just spending resources properly (constantly producing units and workers, setting up infrastructure, etc).

Yeah, interesting! I agree I don't usually hear macro used that way.

But if someone was microing a battle and as a result didn't look at the minimap and see a drop arriving at their base, I can totally see concluding that this player is bad at macro as a result -- macro is referring to there being a macro cycle of tasks you have to perform all the time whether you want to or not, and non-production tasks like checking the minimap and sending in a scout seem like good examples of those tasks too.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#77

Post by ehsankia »

EGreg wrote: post #50
JefeChulo wrote: post #30

"so agents must interact with the game within limits of human dexterity in terms of “Actions Per Minute”." I am really glad they are limiting APM because otherwise things just get stupid.

I would like to see IBM Watson dominate Jeopardy without a superhuman finger.

Yes and no. I guess the more "fair" way to compare them at trivia would be to have a format where all 3 give an answer to every question, and whoever gets the most points wins. That's obviously not really jeopardy, and I'd be curious to know how Watson would perform purely on the trivia knowledge vs clicking speed. I'm guessing it would still win though.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#78

Post by usaphp »

JefeChulo wrote: post #30

"so agents must interact with the game within limits of human dexterity in terms of “Actions Per Minute”." I am really glad they are limiting APM because otherwise things just get stupid.

Would not actions per second be a better limit tho?

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#79

Post by ctw »

artursapek wrote: post #68
aerovistae wrote: post #41

Earlier quoted context omitted.

Awhile. This just isn't like Go or Chess. The gap from perfect information to imperfect information is quite a chasm, and from turn-based to real-time is even more vast. I play Age of Empires 2 semi-competitively, and I just can't imagine the research progress that would have to be made for a pro to lose to an APM-limited AI agent. So much of the game comes down to intuiting what your opponent is planning without bei…

Speaking of AoE 2, I really hope this research ends up benefiting that game. The AI in it has always been so bad but it's still my favorite game of all time.

Have you played against the updated AI in Aoe2 HD?

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#80

Post by gcp »

hitekker wrote: post #59

This seems all in good fun but I wonder if it's come too late. Starcraft 2 is at its twilight. The biggest leagues of South Korea have disbanded. [1] The prolific progamers who transitioned to Starcraft 2 have gone back to Broodwar. [2] Blizzard itself has scrubbed all references to Starcraft 2 on the very home page of Starcraft. [3] Except for the twitter embed, it has only only one "2" character... in the copyright…

I wonder if it's come too late.

Couldn't it be the opposite? Blizzard was willing to do this release exactly because SC2 is dead?

Post reply on HN