Re:DeepMind and Blizzard Open StarCraft II as an AI Research...
by TulliusCicero on Wednesday August 09, 2017 @06:18PM
(#14974251)
It's not literally continuous, but it is real-time rather than turn-based, and positions of units are essentially floats rather than (a small range of) ints. That makes it effectively continuous (too large to just generate a tree of all possible actions and then prune).
Re:DeepMind and Blizzard Open StarCraft II as an AI Research...
by dyarosla on Wednesday August 09, 2017 @06:48PM
(#14974475)
Are you sure positions of units are essentially floats? Given how the units seem to arrange themselves (from what I see), I would guess that it's not close to the full range of floats, and instead there are just a few fractional pixel locations that units snap to. This is just a guess however.
-- If this is the case though, the space could be represented by taking larger integer values (say, a magnitude of 1 or 2 higher) to represent positions at a fractional pixel level (say, in 100ths of a pixel).
Re:DeepMind and Blizzard Open StarCraft II as an AI Research...
by Double_Cast on Thursday August 10, 2017 @09:54AM
(#14979640)
Buildings snap to a grid. Units take up space according to a hitbox. Hitbox size varies according to each type of unit (E.g. Thors are huge). This becomes important when dealing with AoE.
Consider a group of mutalisks. If you select-all and issue an attack-command or move-command, the mutalisks will bunch up tight and then disperse. Cf a video on the "magic-box technique".
So I wouldn't be surprised if position-values were floats.
Re:DeepMind and Blizzard Open StarCraft II as an AI Research...
by winthrowe on Thursday August 10, 2017 @11:17AM
(#14980546)
I haven't looked at SC2 specifically, but would be surprised if they were floats; I sometimes read game dev blogs and RTSs on average tend to be implemented using int/fixed-point based positioning, to eliminate floating point imprecision as a source of multiplayer sync issues.
Re:DeepMind and Blizzard Open StarCraft II as an AI Research...
by TulliusCicero on Thursday August 10, 2017 @05:55AM
(#14978110)
Even if you just bucketized things at the pixel level, that leaves you with a range in the thousands for each dimension.
I haven't looked at if they limit the rate of commands that the AI can issue, otherwise this will be something that can be a very big advantage to the AI once it learns to micro ...