HN Theater @HNTheaterMonth

Perfect micro matters a lot when you zergrush your enemies: https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ mgdlbp

AlphaStar's blink stalker micro, https://www.youtube.com/watch?v=cUTMhmVh1qs&t=5888s

with capped actions-per-minute and reaction time: https://news.ycombinator.com/item?id=18992698

⬐ MaxikCZ

This is what I dont like about Starcraft. The strategy is, in many instances, second to microing the units. The fact that 1hp unit have the same effectivenes as a full hp one is just weird.

Alphastar also didn't play with the same limitations that a human has. Even after removing its ability to see the entire map and finally forcing it to scroll around, alphastar never misclicks (so its APM==EPM) and can still blast nearly unlimited APM for short bursts as long as its "average APM" over an x-second period matched human's APM.

I believe Alphastar would generate more interesting strategies if we limited alphastar to a bit below human APM and forced it to emulate USB K+M to click (instead of using an API, which it currently does) and adding a progressively increasing random fuzzing layer against its inputs so that as it clicks faster the precision/accuracy goes down.

By "interesting strategies" I mean strategies that humans could learn to adopt. Currently its main strategy is "perfectly juggle stalkers" which is a neat party trick, but that particular strategy is about as interesting to me as 2011-era SC AI[0]. Obviously how it arrived at that strategy is quite interesting, but the style of play is not relevant to humans, and may in fact even get beaten by hardcoded AI's.

I'm also very curious what Alphastar could come up with if it were truly unsupervised learning. AIUI, the first many rounds of training were supervised based on high level human replays -- so it would have gotten stuck in a local minima near what has already been invented by humans.

This may be relevant if Microsoft reboots Blizzard's IP. I would love to have an alphastar in SC3 to play against off-line, or have as a teammate, archon mode, etc. I think all RTS' are kind of "archon mode with AI teammate" already. The AI currently handles unit pathing, selection of units to attack, etc. With an alphastar powering the internal AI instead, more tactics/micro can be offloaded to AI and allow humans to focus more on strategy. That seems like it would be super cool.

Examples: "Here AI, I made two drop ships of marines. Take these to the main base and find an optimal place to drop them. If you encounter strong resistance or lots of static defense, just leave and come back home"

"Here AI, use these two drop ships of marines to distract while I use the main army to push the left flank. Take them into the main, natural, or 4th base -- goal is to keep them alive for as long as possible. Focus on critical infrastructure/workers where possible but mostly just keep them alive and moving around to distract the opponent."

0: Automaton 2000 AI perfectly controls 50-supply zerglings (2.5k mineral) vs. 60-supply (3k mineral, 2.5k gas) siege tanks: https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ dwohnitmok

> Alphastar also didn't play with the same limitations that a human has. Even after removing its ability to see the entire map and finally forcing it to scroll around, alphastar never misclicks (so its APM==EPM) and can still blast nearly unlimited APM for short bursts as long as its "average APM" over an x-second period matched human's APM. > I believe Alphastar would generate more interesting strategies if we limited alphastar to a bit below human APM...

No Alphastar definitely had misclicks, and it had a maximum cap on APM regardless of average that was far lower than the max burst of APM (or even EPM) of top players. When I have the time I can go dig up some games where Alphastar definitely has misclicks, and I believe the Deep Mind team has said before that it will misclick. Its APM limits are already lower than pros both on average and in bursts (and are reflected in its play, Alphastar will often mis-micro units in larger, more frantic battles such as allowing disruptor shots to destroy its own units, but it will never make the same mistake with much smaller numbers of units).

> Currently its main strategy is "perfectly juggle stalkers"

Definitely not. That was its strategy in its early iterations against MaNa and is no longer feasible with the stricter limitations in place. Its Protoss strategy is significantly more advanced than that now (see its impressive series of games against Serral with an amazing comeback here: https://www.youtube.com/watch?v=jELuQ6XEtEc and a powerful defense against multi-pronged aggression here: https://www.youtube.com/watch?v=C6qmPNyKRGw) (and of course by "now" I mean when Deep Mind took it off the ladder). Both of these involve an eclectic mix of units with Alphastar effectively using each type of unit and varying it in response to what Serral puts out and its own resource constraints.

A lot of commentators have difficulty distinguishing Alphastar from humans when the former plays as Protoss (its Terran and Zerg play is weaker and often more mechanical).

> I mean strategies that humans could learn to adopt.

My main takeaways from watching Alphastar were "pros undervalue static defense and often have a less than optimal number of workers (where Alphastar's seeming overproduction of workers lets it shrug off aggressive harassment)," but I don't know if those have picked up in the meta.

⬐ runnerup

Edit 2: Reading through the "supplementary data" of the 2019 paper, it definitely appears that the AlphaStar which reached grandmaster was not limited in the same ways as the 2017 paper would suggest. x/y positions of units are not determined visually, but fed directly from the API. So AlphaStar absolutely can just run Attack(Position: carrier_of_interest->pos.x) and not mis-click. It's "map" / "vision" is really just a bounding box of an array of every entity/unit on the map and all the things that a human would have to spend APM to manually check (precise energy level, precise hit points remaining, exact location of invisible units, etc). See [7]. DeepMind showed they have some fixed time delays to emulate human experience, if they had a position fuzzer, they would have mentioned it. I'm reasonably convinced they gave AlphaStar huge advantages even in the 2019 version that was 'nerfed' from the 2018 version. The 2017 paper was a more ambitious project IMO that didn't quite get fully developed.

Edit: 7 minutes after writing this I re-read the original paper[-1]. https://arxiv.org/pdf/1708.04782.pdf page 6 and 7 make it clear that DeepMind limited themselves to SpatialActions, so they cannot tell units "Attack Carrier" but have to say "Attack point x,y" (and x,y also has to be determined visually, not through carrier_of_interest->pos.x ). It's still not clear in the paper if any randomness is added to Attack(x,y).

Additionally, I have some serious concerns about assuming that the design decisions made in this 2017 paper were actually used in the implementation of the 2019 Alphastar demo vs TLO and MaNa. The paper claims "In all our RL experiments, we act every 8 game frames, equivalent to about 180 APM, which is a reasonable choice for intermediate players." I would agree with this choice! But [5][6] indicates that Alphastar's APM spiked to over 1500 APM in 2019! And even in moments when a human reaches that APM, their EPM would be an order or magnitude lower, whereas Alphastar's EPM matches its APM.

Original post:

Thank you so, so much for adding to the discussion! Would love to chat more about this if you see my reply and feel like it.

Regarding "mis-clicking", my understanding was that AlphaStar used Deepmind's PySC2[0][1], which in turn exposes Blizzard's SC2 API[2][3].

Here is the example for how to tell an SCV to build a supply depot:

  Actions()->UnitCommand(
    unit_to_build,
    ability_type_for_structure,
    Point2D(
      unit_to_build->pos.x + rx * 15.0f,
      unit_to_build->pos.y + ry * 15.0f
    )
  );
  

where unit_to_build->pos.x and unit_to_build->pos.x are the current position of the SCV and rx and ry are offsets. It's possible to fuzz this with some randomness, and indeed in the example, rx and ry are actually random (because the toy example just wants to create a supply depot in a truly random nearby spot, it doesn't care where). But the API doesn't attempt to "click" on an SCV and then use a hotkey and then "click" somewhere else. The API will never fail to select the correct SCV. It will also build precisely at the coordinates provided.

Point 1: Even if DeepMind added a fuzz to this method to make it so AlphaStar can "misclick" where the depot gets built, it cannot accidentally select the wrong SCV to build that depot. (Possibly wrong, as they could be using SpatialActions, see below)

Point 2: Most bot-makers wouldn't add a random fuzz to the depot placement coordinates to make their AI worse and I'd be super surprised if there was hard evidence somewhere that Alphastar had such a fuzz. (This is my main concern.)

My personal conclusion was that anything which looks like a "misclick" is, in fact, a "mis-decision". A human can decide "I want my marines to attack that carrier" but accidentally click the attack onto a nearby interceptor. I didn't think Alphastar could do that because I assumed it would use the Attack(Target: Unit) method instead of Attack(Target: Point) in that scenario -- and even if they used Attack(Target: Point) it would be used as Attack(Target: carrier->pos.x).

However, I realize now that they could be doing everything with SpatialActions (edit: it does, see paper[-1] pp. 6-7) (select point, select rect's)[4], and that they could have a implemented a randomness layer to make alpha star literally mis-click.

I suppose I would need to test this API and dive into the replay files to first see if its possible to discern the different between Attack(Target: carrier_of_interest) and Attack(Target: carrier_of_interest->pos.x). Then, even if Alphastar is using the latter, it's still not clear that there's an additional element of randomness outside of the AI/ML control.

Has anyone already done an analysis of the replay files on this level, or has DeepMind released hard info on how they're controlling the bot?

-1: https://arxiv.org/pdf/1708.04782.pdf

0: https://www.youtube.com/watch?v=-fKUyT14G-8

1: https://github.com/deepmind/pysc2

2: https://github.com/Blizzard/s2client-proto

3: https://blizzard.github.io/s2client-api/index.html

4: https://blizzard.github.io/s2client-api/structsc2_1_1_spatia...

5: https://www.alexirpan.com/2019/02/22/alphastar.html

6: https://deepmind.com/blog/article/alphastar-mastering-real-t...

7: https://ychai.uk/notes/2019/07/21/RL/DRL/Decipher-AlphaStar-...

⬐ dwohnitmok

I unfortunately don't have the time to look at the papers in detail (I could totally see how a lot of what I observed could happen even without intentional misclicks so I do take that back), but I want to point out that January 2019 Alphastar (in exhibition matches against TLO and MaNa) is significantly worse than Fall 2019 Alphastar. Alphastar changed very markedly between those time periods.

If you look at an Alphastar Protoss game from the latter half of 2019, it's not relying on cheap tricks to win (such as the impossible stalker micro). Nothing it's doing leaps out as superhuman. Instead it just grinds down its opponent through a superior sense of timing and macro strategy. The two games I linked against Serral it wins by punishing when Serral overextends his reach or by altering its unit composition to better fit what Serral throws at it, rather than some ungodly micro. Nothing it's doing there couldn't be done by a human. In fact I would say in most of the battles, Serral's micro was better than Alphastar's.

Now it's also worth pointing out that Serral is playing on an unfamiliar computer, rather than his own, so there's a bit of a handicap going on and even Alphastar Protoss will still lose to humans, so it's not superhuman, but it's definitely an elite player and its play style is very difficult to distinguish from that of an elite player.

⬐ pretendscholar

Why is it far worse with Terran and Zerg?

⬐ dwohnitmok

I don't know enough to answer "what mechanisms of how the AI works would cause it to be worse than Terran and Zerg."

If the question is rather "what characteristics of Alphastar's Terran and Zerg play style make me say that its Terran and Zerg play is worse than its Protoss play," the simplest answer is that Alphastar just feels a lot more like a bot. Unlike when playing Protoss, it seems to get into certain "ruts" of unit composition and tactics that are a bad match for the opponent it's facing and can't seem to reactively change based on the game is going, whereas with Protoss it seems more than happy to change its play style over the course of the game based on what the opponent is doing.

Just as an example of how extremely unfair it would end up being, flawless AI micro looks like this: https://www.youtube.com/watch?v=IKVFZ28ybQs

100 zerglings vs. 20 siege tanks. Without insane micro the zerglings barely kill 2 siege tanks. With insane micro the 100 zerglings mop up the whole army with ease.

It's fascinating & fun to watch, but if your goal is to make an AI that can out-think a human it's super not useful, either.

It was also really unimpressive in my opinion, instead of being smarter and making broad decisions about tactics that are harnessed by some perfect unit composition knowledge, the AI won on a purely micro scale.

There are videos from several microbots such as Automaton 2000: https://www.youtube.com/watch?v=IKVFZ28ybQs that showcase what super APM can do. The DeepMind AI that beat some pro players did it by having better micro while generally having worse strategies. The DeepMind matches showed how better micro can turn a generally weaker unit composition into the winning unit composition just as that Automaton 2000 video did.

To me it seemed that the DeepMind team figured out that the only way to beat competent players was to do what all those microbots do and pump APM into godly levels. They decided to limit APM, however like you said, just average APM and have the bots explode APM when needed. The real funny match was when MaNa beat Deepmind by completely breaking the AI with generally simple drop strategies and made Deepmind look very much inept.

This is from 2011 https://www.youtube.com/watch?v=IKVFZ28ybQs

I will take this with a grain of salt.

Here’s that perfect zergling video: https://youtu.be/IKVFZ28ybQs

I think you are severely underestimating the APM and micro ability of these bots. https://www.youtube.com/watch?v=udIA6uvWS2Y

I know they have said they will be limiting the maximum APM of the bot to around 180 for the final bot but they may not have implemented it at the time this was happening.

Edit: another example https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ friendlybus

The second example is likely a 'cheat' because the splash damage would be applied the same frame as the shot hits the centre zergling. For an AI to dodge that it would have to have knowledge of which zergling was going to be hit before it was fired upon. The video creator likely used map triggers to simulate the effect.

⬐ EForEndeavour

Here's the original mention of that AI in a teamliquid forum thread started in 2011: https://www.teamliquid.net/forum/starcraft-2/210057-automato...

As far as I can tell, the AI must be cheating, at the very least to obtain map vision beyond what is available in a match. In order for the zerg AI to observe each tank's turret rotation and predict which zergling it's about to fire on, zerglings have a sight radius of 8, smaller than the tank's 11. In a fair match, the zerglings would be fired on before getting a chance to see the tanks. Even as the group of zerglings gets close enough to see the first tanks, other tanks start firing from beyond the zerglings' vision, so I'm not convinced this AI could pull this off in an actual match.

⬐ a1369209993

In the linked video around 1:07, you can see that they already have vision on the tanks when the first one rotates to fire. This could be the result of a cheat, but SC2 does include NPC watchtower buildings that can be captured to grant vision over a large area of the map (you could also send flyers to scout). From there it is (or at least can) 'just' ridiculously fast and precise angle-tracking and micro, so this is a situational tactic at worst.

It makes a huge difference. In this video, 20 tanks kill 100 zerglings and lose only two tanks. With super-human micro, the results are... quite different. https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ vvillena

Reaction time is the real difference in this video. A human can't react to the twitch of the siege tank cannon that happens just an instant before the shot lands, we treat it as something that happens instantly and thus, we can't react to it, not even with a single unit. If you apply a human reaction time to that AI, that behavior isn't possible anymore, even with perfect micro.

For anyone who actually plays SC2, or any real time game where human speed is a limitation, it should not be surprising that AI would crush human opponents.

This video demonstrates why: https://m.youtube.com/watch?v=IKVFZ28ybQs

AI has crushed humans in Go, the most complicated (widely played) board game. I'll be impressed again by AI when it beats us in physical sport.

⬐ jeff18

This comes up every time Starcraft AI is discussed. It's really frustrating. Why immediately discount the incredible work AI researchers are doing by instantly assuming they are using cheap tactics like shown in your video?

When a Starcraft AI is ready, it will be incredibly obvious if it's using brand new builds, strategies, and tactics (which pros will immediately copy for the next $500,000 tournament) or if it's "just" using 10,000 APM to perfectly dodge attacks in a way that a human never could.

I'm guessing Google and Tencent are going for the former instead of the latter.

⬐ tfha

You could fix this by capping the apm of the AI to 500

⬐ Kagerjay

I would cap it at 300apm, thats how high most professional koreans are IIRC. But that 300 apm is 90% redundant mouseclicks though

⬐ arayh

I feel like "useful" APM and "raw" APM are very different for humans than it would be for AI. You can technically get an AI to "optimize" their actions to the minimum required for the end result, but humans tend to frantically waste actions during a game.

⬐ arayh

I'd really like to see Starcraft AI do counter builds and fake out human opponents with falsified scouting information. I can see AI eventually becoming good at information manipulation and taking advantage of human psychological tendencies.

⬐ mattnewton

I’m pretty sure that program in the video has access to internal game state to know which zergling is targeted, because it splits them when the tanks are out of sight, and always picks the right zergling. A real bot wouldn’t have access to this state, and the one in the article doesn’t. Marines vs zerglings+banelings would probably be a better micro example showing theoretical bot perfect-but-fair micro.

In any case, this can be solved by capping the actions per minute near Pro human levels, somewhere in the 300-500 range.

There are still incredible strategy problems to be solved that cannot be overcome with perfect micro. Figuring out a build alone using RL (which is what I think this paper is doing) is still a huge step.

⬐ aurelwu

Deepmind states in their released papers that they limit the actions per minute for the AI so it doesn't just win via speed. Their current approach is a bit simplistic and does not really reflect how humans perform actions but they want to keep it somewhat fair on the "mechanical" aspect of the game. OpenAIs Dota Agent also has similar restrictions although it has shown super human reactions in some cases. This should be tweakable in such a way that the Agent is on a human level and needs to actually be better at the decision making.

⬐ Kagerjay

Anyone who's played starcraft competitively knows how much infinite potential there is to micro control, much more compared to Dota2, and that even the best players can't reach that level either by a very large margin.

Dota2 is not the same way - some of the best players perform micro-control on par with AI. This makes AI in DoTA much more impressive

⬐ na85

To me, the way you've explained it makes DOTA less impressive as a game.

⬐ Kagerjay

Starcraft focuses more on mostly one critical pivot micro battle, and many compounded macro processes leading up to that point.

Dota II focuses more on compounded micro decisions throughout the entire game for sometimes 60 mins+. Dota II revolves around using your one hero (with the exception of meepo), and teamwork much more heavily. The amount of different scenarios in DoTA II is significantly higher because of all the different heros, skills, levels, and combinations thereof.

Starcraft has very predictable scenarios though. There is usually less than 10 meta builds at any given competitive nerf/post patch balance. Dota II is hundreds if not thousands, per hero, per team composition, etc. So AI is way more impressive in Dota II

⬐ na85

>There is usually less than 10 meta builds at any given competitive nerf/post patch balance. Dota II is hundreds if not thousands, per hero, per team composition, etc.

There are hundreds if not thousands of builds for each hero?

⬐ kentosi

What would be interesting is if they limited the AI's ability to that of humans. Ie - simulate how fast a human could potentially group select and point-click, etc. Now THAT would be interesting.

Until then, yes as you put it, the AI would crush humans and unfairly so.

⬐ jlawson

Build a set of robotic hands with human nervous system-like control inaccuracies and delays. Put it on a mouse and keyboard. Point a camera at the screen (tuned to match human visual acuity and eye movement speed and focal area), put headphones on a mic, let the AI play the way humans do.

⬐ Xichom2k

Go is a perfect information game. RTS are not.

And the micro advantage is not all that relevant since APM and latency restrictions can be imposed on the AI to force them to play under conditions comparable to human players.

⬐ roymurdock

Depends on whether or not the AI can see through the fog of war. In some RTS the "insane" level AI has full knowledge of the map. But yes, if it has limited info, like human players, the strategy is much different and much harder for an AI to intuit compared to chess or Go. Unless the winning strategy in the game allows for constant scouting, but is unlikely due to the waste of resources on that unit

⬐ baddox

If you actually play SC2 (or more significantly, if you follow the professional competitive SC2 scene), you should definitely expect AIs to be a looong way away from competing with professional humans. A pro human with an AI assistant (either to micro for them, like in that video, or macro for them) would obviously be able to beat another pro human on their own, but an AI by itself won't stand a chance with current AI.

⬐ pythonaut_16

I would watch an AI-assisted human tournament, especially where each team is responsible for designing their own AI

⬐ baddox

It would certainly be interesting. In professional SC2 competitions even simple input macros like fast-repeating clicks or keystrokes are banned. It would likely be a massive advantage.

⬐ justfor1comment

I play SC2 as well as work on AI/ML during my day job. The state of AI is extremely hyped by the media. The most sophisticated neural networks I have seen so far are recommender systems. The algorithm that predicts which next movie on Netflix you might be interested in based on your history of completed and abandoned movies. However, for all such systems there is a precise way to measure the effectiveness of the AI and improve it by doing A/B testing etc. Main problem with SC2 and AI is there isn't a good heuristic to measure your progress at any point of time. Eg: If player 1 has 25 reapers and player 2 has 8 void rays who is ahead? Well the void rays could destroy all barracks and win or the Terran player might make a few marines and missile turrets to counter the void rays while attacking probes with reapers. Basically, if you pause an SC2 game at any point of time(barring last 2 minutes) you cannot predict the winner with 100% accuracy. This is a big problem for designing an effective AI for SC2.

⬐ Kagerjay

It would greatly depend on positioning and chance of person winning fluctuates depending on the number of optimal moves available, similar to GO but more complex since there is so many scenarios.

Also you have to consider whether voidrays have speed upgrades, same with repears. Terran can play with fog of war too and lift off, usually terran has an advantage here

⬐ Nasrudith

Also a factor is that the game is balanced for human inputs. As many crazy micro trick videoes demonstrate by doing things like optimal gapping zerglings against siege tanks.

If players could do that reliably we would start seeing major unit changes. It already happened to the original void rays who would do things like attack themselves to maintain charge to keep massed annihilation capability.

⬐ mattnewton

Players can’t do that mostly because it would be impossible to correctly determine which zergling was targeted, this bot has access to perfect game state information from the sc2 editor api and it looks like it is using it to me.

However, a bot could use just the same information a player could theoretically have access to but humans can’t pay attention to it all at once- that would be a real advantage. This one is basically cheating extra information though.

⬐ kirkules

Why doesn't human speed/physical strength lose out in physical sport controlled by AI as well? Isn't the analog of letting an AI take actions in SC2 as fast as it can make decisions just letting an AI control some robotic body arbitrarily better at tackling and running and whatever other relevant physical attributes than humans are?

⬐ benchaney

Machines winning at physical sports has already happened. It is even less impressive than any AI winning at real time games. A race car is faster than a human runner. A speedboat is faster than a swommer. A tank would be an untackleable running back. A rail gun Tennis serve would be unreturnable (etc)

⬐ pmontra

Yes but probably parent meant a fully automated opponent, e.g. not car + human driver but an autonomous car. That probably beats any human in Olympic running races even now. Robot tennis player, not yet.

⬐ rtkwe

That's not just super human reflexes it's using information no player connecting through the normal interface has.

⬐ TulliusCicero

The article is talking about their AI crushing other AI's, not humans. There aren't any AI's right now that can beat high level human players, even with superhuman reflexes and control.

> AI has crushed humans in Go, the most complicated (widely played) board game.

In terms of ruleset, Starcraft is at least a few orders of magnitude more complicated than Go. It doesn't feel more complicated to humans, really, but the sheer number of variables at play is vastly higher.

⬐ KevinCarbonara

Starcraft 2 is not "orders of magnitude more complicated than Go". It's far less complicated in terms of options, and far more complicated in terms of factors like speed/reaction time that don't exist in Go. Those things are difficult to compare at all, but certainly do not qualify as "orders of magnitude", which is measurable.

⬐ ZeroBugBounce

> It's far less complicated in terms of options

Could you explain how you figure that in more detail?

I mean, to my untrained eye, it sounds like it wouldn't be so, since in every time slice of the game (equiv. of a turn in Go?) you can have hundreds of points of control - hundreds of levers to choose to pull - and of course that's in every frame (or whatever interval the UI actually allows you input).

⬐ TulliusCicero

It absolutely is, which is partly why there aren't any good AI's for it yet, even though we have ones that can crush the best players in the world at Go.

Go's game state, for example, is very small. You can pretty much represent it with a 19x19 array of 2-bit variables, because each space only has three possible states. That's only 722 bits. Maybe a few more to track whose turn it is and how many pieces each player has remaining.

In contrast, Starcraft can have hundreds of units in play from dozens of types, each of which usually has at least a position value (x and y) and a health value, and commonly has other things like energy value and cooldown values. And each of these you'd need at least a 16-bit int. And that doesn't even get into the enormously larger possible action space for each "turn".

⬐ jtolmar

Brood War has a significantly higher branching factor than Go: each of ~50 units can receive 3 orders with arbitrary targets (the untargetted ones hardly matter for branching). The map is 4096 x 4096 pixels, though some of those are functionally identical so say 256 (the number of angles a unit can face). So branching factor around 38400. The game runs at 24 fps, and the average game is 20 minutes long, for 480 turns. 38400^480 is a number with 2201 digits.

Starcraft II runs at a higher frame rate and uses higher resolution maps, so these numbers are even more ridiculous there.

⬐ TulliusCicero

> game runs at 24 fps, and the average game is 20 minutes long, for 480 turns.

Messed up your conversion there, fps is seconds and you had game length in minutes, so need to multiply by 60. So that's 28,800 "turns".

> This game favors Macro over Micro oven more than Dota2 and the original StarCraft.

Only at human speeds.

Once you break the 10,000 APM barrier however, Zerglings start to dodge-tanks and other shenanigans begin to happen.

https://www.youtube.com/watch?v=IKVFZ28ybQs

Micro has a general advantage of growing at a rate of N^2. That is, 10 Zealots, with perfect micro, can perform roughly as well as 100 Zealots with the worst micro possible.

Ex: 100 Zealots come in one-at-a-time vs the 10-zealots in an inverted-V shape. The 10-zealots will defeat roughly 100.

The bigger and more complicated the board gets, the more and more micro becomes favored.

Frankly, superior reaction time and other mechanical skills in Dota2 (or Starcraft, or other games which are being tested) makes me think that a typical AI would beat a human.

https://www.youtube.com/watch?v=IKVFZ28ybQs

That's the "gloves come off" AI. Granted, its a problem solved by raw, mechanical button-pushes at a rate beyond what is possible on a keyboard/mouse, but it demonstrates the greatest skills an AI or computer has.

Of course, no one wants to see an AI beat a human using known methodologies. They want to see an AI win at the abstract game of "a game of strategy".

From this perspective, I think the poker AI results over the past year or two have been far more interesting. AIs figuring out the Nash Equalibrium and playing bluffing games around it.

Sure, its a bit mechanical and mathematically inclined, but generalizing and solving the bluffing game is IMO far more useful.

dota 2 is not as extreme about this as, say, starcraft. in starcraft, most "strategies" are heavily scripted build orders that almost never deviate from a handful of openings (similar to opening moves in chess) and a large amount of winning comes from the ability to quickly give orders to your troops ("micro"). This is an example of a strategy that is not viable without superhuman reactions: https://www.youtube.com/watch?v=IKVFZ28ybQs if you directly attack 20 siege tanks with 100 zerglings you will only kill about two siege tanks, but an AI can kill all the siege tanks with some zerglings left over.

There's some of this in dota, but there's a cap on the skill level for most playable characters that pros generally get "close enough" to, and beyond that the strategic depth comes from area control decisionmaking. Theres over 100 heroes and many of them have really weird abilities, like the possibility of creating a temporary wall (earthshaker) or the ability to teleport anywhere on the map every 20 seconds (furion). I could be wrong though, maybe the AI is winning games by playing heroes with long range and perfectly microing them to harass and prevent the other team from ever getting gold/xp.

⬐ eerikkivistik

I think we made the same point at the same time :D

⬐ halflings

> in starcraft, most "strategies" are heavily scripted build orders that almost never deviate from a handful of openings (similar to opening moves in chess) and a large amount of winning comes from the ability to quickly give orders to your troops ("micro")

As somebody who plays StarCraft casually (gold/low plat in ladder), this is not true. It's even less true for pro players. The level of strategy in StarCraft is impressive, it's really hard to guess in which direction games will go when two very good players are playing against each other.

Sure, perfect execution when it comes to one strategy (say, mech-heavy Terran) will give you the largest advantage against your opponent, but failing to scout appropriately and guess what your opponent is up to means your strategy is dead. You also have to decide when to attack, how much you're willing to sacrifice to damage somebody's economy, when you want to focus one economy vs building units, ...

The video you sent with zerglings is a gimmick made for fun (it's a hard-coded AI using the siege tank's aim logic to divert zerglings from that). That would not win you a game. (because most likely a pro Terran would have destroyed your base before that)

⬐ fizx

I wonder how far you'd get with a bot that macros perfectly but also A-moves 2-3 groups.

⬐ halflings

What does "macro perfectly" mean? If it does the same strategy over and over, you just scout, find its strategy, and go for the counter. Its macro will be useless if it has the wrong type of unit.

In a way, the built-in AIs "macro perfectly", but they are terrible at strategy and fighting (because even fights are not just a matter of gimmicks, you need to split units in a special way, send diversions, attack at the same time from multiple fronts, etc.)

Yes, they start punching way above their weight against tanks, too. Even moreso if you throw in an auto-scatter script.

https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ invalidOrTaken

What about tanks on high ground and out of reach? What if the roaches have to funnel through a walled choke guarded by some MMLib as well?

That might seem contrived, but there is a player whose job is to contrive it!

No, I don't think the next patch should include "improved" roach AI. But deep strategy games like Starcraft tend to have multiple levels on which to do battle, and you can often nullify an opponent's insurmountable advantage on one level by doing battle on another level. I honestly think that if super-roaches like we've been discussing were patched into the game, with no further changes made, winrates would stabilize around 50% in a few years (assuming everyone hadn't quit in disgust).

Now, that might not be the game you'd want to play. I'll freely admit I wouldn't want to play it. But that's you and me---perhaps whoever's into chess would love it. And "This would no longer be fun for me," while perfectly legitimate, is a very different claim than "the game balance breaks."

⬐ lodi

> ...deep strategy games like Starcraft tend to have multiple levels on which to do battle...

That's exactly the point; the "other levels" are macro, micro, and multi-tasking--the "realtime" components of an RTS game. (I consider positioning and scouting a factor of micro and multi-tasking respectively.) Those are the facets of the game that let you take two equally matched strategies, execute slightly better than the opponent, and thereby eke out a gradually compounding advantage.

If you remove those, the "deep strategy" of starcraft is basically just doing the one or two counterplays that you obviously need to do to survive. "He built too many early game marines so now I build banelings or I die." The strategic "if he does this, I'll do this, but then he'll do that" decision tree is very shallow in a game like brood war or sc2.

> What about tanks on high ground and out of reach? What if the roaches have to funnel through a walled choke guarded by some MMLib as well?

Then I'll be forced into one of a small handful of tictactoe-like responses: brood lords, vipers, doom drop on top of your army, or pull you apart with muta/nydus multi-taski... no wait. Just the first three options I guess.

A 'perfectly' micro-ing AI is both boring to implement and boring to play against. Somebody made one for SC2 back when that was popular, take a look at these videos to see how uninteresting it would become after the first attempt.

https://www.youtube.com/watch?v=0EYH-csTttw

https://www.youtube.com/watch?v=IKVFZ28ybQs

https://www.youtube.com/watch?v=DXUOWXidcY0

⬐ make3

yeah but I'm pretty sure these bots still get crushed by humans because of macro, planning and positioning, which is why it takes top firms on the planet so long to solve the problem

⬐ AmericanChopper

If the AI wasn't very smart, then you'd expect there to be some optimal path that would beat them. But Starcraft has always been a game with very little skill ceiling on micro. Well micro'd units have the potential overcome huge macro advantages. A famous real-world example would be Boxer's Immortal Marines:

https://www.youtube.com/watch?v=WJp0t9n8DWk

⬐ TulliusCicero

But even the best AIs in Starcraft are still quite bad compared to competitive players.

Check this out. 100 zerglings vs 20 siege tanks - https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ taurath

Interesting. It seems that this is possible mostly by the lag time between target acquisition and firing by the siege tanks, compounded with the relatively high speed of the zerglings - most any other unit in the game wouldn't be able to react in time.

For human vs AI there will have to be APM rate limits otherwise the AI can win with no real strategy[0].

For AI vs AI it could be interesting to see what strategies develop with two opponents with the ability to perfectly microcontrol their units.

[0]Zerglings vs Siege Tanks when controlled by AI with perfect micro.

https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ foobaw

I think even with unlimited APM, humans can still beat AI using cheese strategies, like an undetected cannon rush, since you can't really micro your workers against cannons (the projectile isn't dodge-able like the one from siege tanks).

Otherwise, you make a fair point and that video is amazing. AI vs AI strategy with unlimited APM would be very exciting to watch.

⬐ tialaramex

It is generally assumed that SC and SC2 are not actually just Rock Paper Scissors. That is, you're not obliged to guess your opponent's strategy and counter in the dark but can instead "scout" and figure out what they're doing and overall this can beat a "blind" strategy like cannon rush that doesn't respond to what the opponent's strategy is.

For example the "All ravens, all the time" Terran player Ketrok just responded to the surge in popularity of Cannon Rushes by making a tiny tweak to his opening worker movement. The revised opening spots the Cannon Rush in time to adequately defend and thus of course win.

>The units basically just dance at maximum range, magically dodge hits, etc.

While it certainly isn't fair to play against, it does have a certain elegance[1].

There's also the problem that even if it's AI vs AI, the races and units are balanced around reaction times of humans.

[1] https://www.youtube.com/watch?v=IKVFZ28ybQs

"In what universe is taking 10,000 actions per minute an easier problem for a neural net than 100 such actions?"

StarCraft is precisely such universe. If you could micromanage units perfectly, you can do some amazing tricks. Here's an example of what I'm talking about: https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ SmallDeadGuy

I'm imagining an AI war where the next advancement is the micro of the siege engines to optimise targets and timing of shots to hit large groups after the initial splash avoidance. AI on both sides keep trying to maintain a one-step-ahead strategy which minimises/maximises casualties based on predicting the exact shooting/dodging strategy of the opponents. Will be interesting to follow developments in this area!

⬐ aerovistae

That's a rules engine, designed to do basically one specific thing. It was told how to micro. In that context APM is a meaningless constraint. May as well ask how many times you can print a message in a for-loop per second. yes...quite a lot, and the computer is unfazed by the workload.

This is a different type of bot we're talking about here. A neural net could not learn to work with unlimited apm more easily than limited apm. That just doesn't make sense. That's like saying it's easier to compute 1000 hashes in a second than it is to compute one hash in a second.

When Watson won at Jeopardy, one of its prime advantages was the faster reaction time at pushing the buzzer. The fairness of that has already been hashed out elsewhere, but.....

We already know that computers can have superior micro and beat humans at Starcraft through that(1). Is DeepMind going to win by giving themselves a micro advantage that is beyond what reasonable humans can do?

(1)https://www.youtube.com/watch?v=IKVFZ28ybQs as one example

⬐ mattnewton

That example might be misleading because I assume the AI has perfect information- I don't know how it could know which zergling was targeted before the tank fire landed without knowledge of the game's internal state.

In any case I saw in the comments above they are planning on limiting the APM. But right now they're not at the stage where they can compete with the in-game rules based AI, so it may be a little while.

⬐ Waterluvian

Thanks for that video. That's exactly what I hope to see. AI vs. AI with insane micro capabilities. I want to see SC2 played as close to a "perfect" game as possible.

⬐ ktRolster

Yes it would be amazing to watch

⬐ sidusknight

Alternatively, http://www.youtube.com/watch?v=DXUOWXidcY0&t=0m50s

⬐ jahabrewer

I wonder if limiting APM would be a simple way to make the AI's play more "human" and less exploit-y.

⬐ ktRolster

Limiting APM is definitely a step in the right direction, but there are ways to have super-human reaction times, beyond what a human can do, even while limiting APM.

So if we watch a match and see things that no human could physically do, we will know that the machine didn't win because of intelligence.

It would still be great, it just would be a simplification of the problem.

⬐ chii

What if the ai machine predicted very accurately what their opponents would do? Does that count?

⬐ obastani

My understanding is that in a full match, AIs still have no hope against humans, since even though they can crush humans at micro, their macro is still abysmal [1]. I'm not aware of a match where any AI has beat a pro human player at Starcraft -- I'd be interested in learning otherwise!

[1] http://spectrum.ieee.org/automaton/robotics/artificial-intel...

⬐ TulliusCicero

It's not that their macro is abysmal (macro in Starcraft refers to the mechanics of managing production and economy), it's that their strategy and tactics are real bad.

⬐ flamedoge

would you love to be proven wrong?

⬐ None

None

⬐ sidusknight

Of course.

⬐ apetresc

That's because there hasn't been too much concentrated effort on this problem yet, since you'd have to spend quite a bit of effort just integrating with the game engine.

Certainly a lot less research has been done on computer SC2 than computer go, and nobody expected a pro to be beaten there 1.5 years ago, either.

Yeah, I remember this vid with zerglings doding siege tanks shots: https://www.youtube.com/watch?v=IKVFZ28ybQs

The difference is quite drastic.

It's possible but it's a lot more context-driven than you think with a human involved. The bots do great against each other with their strategies and muscle-memory stuff. Throw a human in the mix, they start noticing patterns in how the units are managed, what strategies are likely, etc. They've exploited these in the competitions to hilarious effect. Here's the main site on prior work & results at the competitions:

https://www.cs.mun.ca/~dchurchill/starcraftaicomp/reports.sh...

Here's a few examples of how the muscle-memory approach, esp if focused on unit vs unit, can fail against humans.

" In this example, Bakuryu (human) notices that Skynet's units will chase his zerglings if they are near, and proceeds to run around Skynet's base to distract Skynet long enough so that Bakuryu can make fying units to come attack Skynet's base. This type of behaviour is incredibly hard to detect in a bot, since it requires knowledge of the larger context of the game which may only have consequences 5 or more minutes in the future. " (2013)

Note: At this point, they also sucked at building and expansion strategies which surprised me since I thought a basic planner would be able to do that. The constraints between rate of expansion, where to place stuff, what units to keep/build, and so on get really hard. The other thing they weren't good at was switching strategies mid-game based on what opponents are doing.

" despite Djem5 (pro) making the bots look silly this year... they were able to defeat D-ranked, and even some C-ranked players. After the human players have played one or two games against the bots they are then easily able to detect and exploit small mistakes that the bots make in order to easily win the majority of games... " (2015)

I don't have the 2016 result yet. It's clear they're getting better but there's a huge leap between bots and humans. Gap seems to be context, reading opponents, and expansion. Now, if they can fix those, they have a chance of taking down pro's combined with the machines inherent strength in micromanagement and muscle-memory on specific attack/defense patterns.

Examples below of the AI's managing units in perfect formation & reaction below. It's like an emergent ballet or something. The second one could be terrifying if they can get it into real-world military. Figured you might enjoy these given your position. :)

https://www.youtube.com/watch?v=DXUOWXidcY0

https://www.youtube.com/watch?v=IKVFZ28ybQs

Counterexample: https://www.youtube.com/watch?v=IKVFZ28ybQs

AI already beats humans at StarCraft, not because it's smarter, but because it can control all the units simultaneously.

https://www.youtube.com/watch?v=IKVFZ28ybQs

https://www.youtube.com/watch?v=3PLplRDSgpo

https://www.youtube.com/watch?v=XgfTpU-a8D0

Really rudimentary AIs are already significantly beyond the skill of humans (in terms of micro, at least).

https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ ygra

As you note, that's only micro, and it's the easy part since you can do most of that with rather simple rules and just high apm (which is where the benefit compared to human players comes from). The interesting part for AI is how to get there, the longer-term planning, recognizing the enemy's strategy based on what it observes, reacting appropriately, etc. So far those are the things AIs have trouble with.

⬐ dwaltrip

They are quite terrible at all of the other aspects: macro, broad strategy, tempo & timing, planning tactical surprises, etc.

This results in a very low overall competency, when it comes to winning games against highly skilled opponents.

It will be a challenge for researchers to improve performance in these areas. The problem space is very complex -- it makes solving Go look like a cake walk in comparison.

A big part of Starcraft is that certain units counter other units. Tanks counter zerglings, because they do splash damage to a bunch of them at once.

Here's what you can do with infinite APM: https://www.youtube.com/watch?v=IKVFZ28ybQs

It's just broken. It's not even the same game.

⬐ pavel_lishin

A nice illustration of the potential battlefield of tomorrow.

⬐ otempomores

Privat third in first row you ve been ai selected to draw splash damage for king and cuntry. Everybody else give him some privacy

⬐ spdionis

"cuntry"... the irony...

⬐ ethbro

That sounds not unlike some of the battlefield reasoning Morgan puts in the post-cyberpunk Takeshi Kovacs series.

Winning against AI in a sufficiently complex game looks very different than winning against a human.

⬐ theptip

I enjoyed this, thanks for sharing. Pretty cool.

⬐ defen

How does the AI "know" which Zergling is going to be fired upon? Are the tank shots not instant-hit? Or is this just a demonstration of what actual optimal control would look like.

⬐ detaro

The tanks aren't given overriding manual commands, so it likely could just predict how their automatic targeting works. If a player would give commands, it could get at least some information from the animation frames before the target is aquired and the shot fired.

(The implementation in the video likely just cheats and gets the information from the engine, but at least the first case should be deterministic enough)

This was an example of extreme micro that a very simple AI can do that changes the game entirely:

https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ lightbyte

And that was created through the games editor I believe. Imagine how much better they can make something with full support for AI development.

⬐ icelancer

Unbelievable! From 2011 even! That's awesome. Can't wait to see more detail on this going forward.

⬐ wlesieutre

How does it seem to know which zergling is about to get hit?

⬐ acomar

If you slow it down, it would be apparent to you too. High-level human players do this kind of thing to, just not this fast. But effectively, it's watching where the attacking unit is facing and it knows when the next attack is coming, so it knows what the viable targets are and can react when it becomes obvious.

(it's also possible the system is receiving information directly from the game engine, but it's definitely possible to figure this out from nothing but the information on screen)

⬐ caylus

Because the tanks are using the default unit AI, which AFAIK amounts to "when your weapon is ready to fire, shoot the closest enemy in range". The zergling AI knows the attack range and rate of each tank so can ensure that the closest zergling is always on its own when a tank is ready to fire.

What would be really interesting is putting a similar smart AI on the tanks, which could make decisions like shooting at the highest concentration of zerglings instead of the closest one, or holding its fire if one lone zergling is in range, but a clump of them is about to enter range.

Human players already do both optimizations with widow mines, which are a unit that takes several seconds to prepare its shot so it's feasible to retarget. It's not feasible for humans to do this with tanks though as they fire immediately and automatically.

You could even see counterevolution as two AI algorithms become better at predicting what the other will do.

⬐ placeybordeaux

Game theory dictates that you shouldn't anticipate what your opponent is likely to do, but rather assume that they will chose the best choice available. Given that you need to move the zerglings before the tank fires the tank should be able to retarget and always hit the highest concentration. That being said organizing your lings to run in a formation to never expose any to splash shouldn't be too hard.

Unfortunate. I personally would love play against an AI with strong game sense as well as insane micro a la https://www.youtube.com/watch?v=IKVFZ28ybQs

And as cool as that is, this is even more terrifying, as a hundred zergslings dodge seige tank cannons and destroy them.

https://youtu.be/IKVFZ28ybQs

It's enough to make you scared for the future of humanity.

⬐ nickpsecurity

What... the... hell..!? That's basically what they show on movies where the action stars have superhuman movement. Except, it's zergling's perfectly coordinating the demolition of siege tanks. Awesome demo of AI micro.

That's incredible. The speed advantage here: https://youtu.be/IKVFZ28ybQs Brings to mind the power of high frequency trading

From an above poster: https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ bottled_poe

The developer of the AI in this video even states that this AI is applies 300 APM per unit. That's 30000 actions per minute. There are simply not enough decisions to make in League of legends to make use of that power.

Well, anyone who says that advantage in micromanagement is not a big thing should see "Automaton 2000" videos. Given that automaton is a map script and thus can have virtually unlimited APM, it beats people from a horribly disadvantageous positions (40 banelings vs 21 marine [1], or 100 zerglings vs 20 sieged tanks [2]).

[1]: https://www.youtube.com/watch?v=DXUOWXidcY0 [2]: https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ diskcat

Yeah. infinite apm would make stuff like marine being able to turn around and shoot instantly OP. it was just impossible to exploit before with human reflex.

also the APM is not unlimited, it is only very high.

⬐ HCIdivision17

Watching the zerglings somehow wash through that tank barage was just ... demoralizing. Those little buggers are not supposed to be a hard counter to tanks, dammit! Fighting against Automaton 2000 is like having your own personal Kaizo assaulting your base.

I think this really demonstrates why putting in APM limits is super important, and as brought out elsewhere also making the computer input via mouse/keyboard and get data from the screen (maybe just a filter to ease up on the CV bits?). A lot of the fun in watching a StarCraft map is seeing how the big picture is balanced against the details, and where a person's limited congnition flows from one focus to another. Limited knowledge and scope of sight play a huge part in the skill.

But mostly I'm just ranting because dodging the splash damage feels unfair; goes against everything I stand for. Next we'll start seeing 5 Skill Rays bulldoze the map! (I'm going to be looking into this a lot more after work - it seems like a super cool project!)

⬐ mizzao

Agreed. It also wouldn't be very interesting to watch a human-AI game where the human is better at planning and tactics but the AI just wins even uphill battles due to insane micro.

⬐ coryfklein

I would LOVE to see an AI vs AI game though where the AI had no restrictions on APM/micro.

I mean, what would an AI come up with given just mass zerglings vs mass zerglings. Would love to see the strategies possible with near unlimited attention and APM.

⬐ LetaBot

You can always watch the StarCraft AI stream: http://sscaitournament.com/

⬐ Monory

Problem with that lies in different balancing.

For example, while banelings, are considered hard-counter to marines, stimpacked marines are still faster than even speed-banelings not on creep and just a little bit slower on creep. Pros use splitting to minimize damage, but here, as you can see, it can be just ultimate showdown.

Another example would be high templars vs ghosts. It is fairly difficult for Terran player to target high templars, but just two EMP shots basically puts templars out of combat, and miss of those shots renders ghosts mostly useless.

So, any area-of-effect attacks would be mostly useless due to infinite APM. That means minus colossi, tanks, banelings, thors and many other units. Probably that means that some race will be somewhat (or, maybe, insanely) overpowered (my bet is on Terran due to possibility of multiple drops, which themselves could be useless, though (because AI can't "miss" a drop), and stim-marine micro). So, the game will require massive rebalancing.

⬐ liusiqi43

For Atari games, they limited actions to 50Hz, which is not entirely out of reach for human beings. I guess they would do something similar to make the SC challenge fair as well.

⬐ shultays

how does the siege tanks vs zerglings work? how do AI know which zergling is targetted? Also was there a delay for siege tanks after it selects a target but before shooting it down? Wasn't it instant like marine, can't remember it.

Or maybe it is because opponent is also AI and automaton simply knows which target it will auto pick.

⬐ Monory

All tanks have limited and fixed range, so Automaton just instantly splits all zerglings from the one which comes first into tank fire range. It IS instant, but highly deterministic, at least their first attacks are. And after their first shot, due to long cooldown, all zerglings are just already attacking tanks in fairly split manner and mostly unkillable by tanks anymore.

⬐ nickpsecurity

I agree. It's one of only areas the AI's have been hood at. Pathfinding and build orders being other two. AI should be limited to a specific number of actions a minute comparable with opposing player or best human champ. Then, we're grading it on its "thinking" instead of dexterity.

They better keep fog of war on too.

⬐ derefr

Or, the AI could be set up like AlphaGo was: as a computer giving instructions to a merely human player. I'd love to see what a powerful StarCraft AI would do if trained to "predict and compensate for" not only its opponent, but also the inevitable human errors in faithfully executing its strategy. A certain Sector Command and Control Unit springs to mind...

⬐ nickpsecurity

The game moves too fast for that. When I contemplated it, I was going to let the AI do the micro battles and build orders. The other aspects are planning one's strategy, identifying opponent's strategy, counters, bluffs, and so on. Humans are best at this. The machines have been laughably easy to beat at it so far.

DeepMind's system is all about finding patterns. It might do better on those aspects. It could even be trained to recognize some aspects of enemy intent, how the battles are going, etc. Thing is, there's lots of potentials for curveballs in Starcraft compared to Go or Atari games. Human pro's curveball on demand. Should be interesting to see what it can do.

⬐ derefr

Hmm. Instead of purely focusing on macro, what if the human was in the middle, while the AI existed at both the top and bottom?

I'm now thinking more explicitly of the book series I alluded to (The General series by S.M. Stirling and David Drake): the human is a commander, so the units are intelligent in their own right (thus, handled by the AI); and the AI is also giving the human commander real-time advice based on what knowledge it can discover through the human's vision (isolated from the other AI-instance doing micro, but "smart" in the sense that it can assume that the micro is being done by a [fallible] rational actor that thinks like it does.)

I feel like that "human in the middle" configuration would actually make for its own new subgenre of 4X/RTS-like games, if we could get it right; somewhat like a more interesting version of tower defense. Like an RTS, it would be about issuing orders; like a MOBA, you'd have direct control of a "champion" unit. But the job of the unit would be to give those orders, and your job as the player would be to get their position fortified while also gaining enough information to accurately strategize.

Come to think of it, this is what Dungeons & Dragons was originally supposed to be about, wasn't it? Commander-level characters going off to do scouting or other special ops for their army, advancing in rank and gaining underlings in the process. (D&D1e assumes you'll just already have a wargame going with an overworld hex grid, unit stats, etc., and just serves as a "what heroes do in a zoomed-in view" add-on to it. Thus why it doesn't come with its own battle system.)

⬐ nickpsecurity

"the human is a commander, so the units are intelligent in their own right (thus, handled by the AI); and the AI is also giving the human commander real-time advice based on what knowledge it can discover through the human's vision "

I see what you're saying. Yes, I daydreamed about such models too. I got excited about two games that stepped into that direction: Supreme Commander's dual-monitor setup with a macro, commander-like view plus detailed, micro view; Full Spectrum Warrior and Full Spectrum Command. The S.C. setup shows people are dabbling in interfaces that might lead to that. FSW and FSC are straight implementations of what you describe: commanders controlling AI agents that are semi-autonomous and provide feedback. FSC isn't available to public but is what I wanted more: limited commander view with data on your troops, position, intel coming in from video feeds or satellite, and so on. A hybrid model might let me go Harbinger and "assume direct control" of a character or team.

"I feel like that "human in the middle" configuration would actually make for its own new subgenre of 4X/RTS-like games, if we could get it right; "

It could. I'm not sure what it will look like outside Full Spectrum Command or bots in shooter games. A lot of the experience comes from the style of the people playing plus their quirks. The Call of Duty Ghosts AI shows that we might be able to approximate that as it did it so well I thought I was playing online against rookies lol. Most fun bots ever were.

"Come to think of it, this is what Dungeons & Dragons was originally supposed to be about, wasn't it? "

I think it was meant to enable and constrain the imaginations of players so the game took place inside their head. I never played it but it was a brilliant idea. Come to think of it, you're onto something here because games like Skyrim have all kinds of autonomous people doing certain routines or behaving in certain ways. There's even contractors and mayors. Any of these people could benefit from AI. Just a matter of computing resources. Could have one world where everyone plays the same world whose characters are controlled via a server farm at developer's location. I originally envisioned that for Runescape when I failed to get them to create a version of it for AI research. It would've been great for testing pathfinding, build systems, strategy, chatterbots, and so on. Skyrim more so.

Note: We could also test a collective intelligence where individual agents publish what they learn to central forums organized by topic. AI expansions could take time to periodically scrape that, try to understand it, and factor it into their gameplay. Basically, simulating player help forums that humans use. Additionally, could build superintelligences, gods, or advanced/E.T. AI's that tap into that plus much of world state that shouldn't be available. Even let them make changes to map or items with that dynamic factored in.

Lots of potential that might not have been explored yet but could make even simpler bots a lot more fun to watch. ;)

⬐ dragontamer

A huge amount of Starcraft is the intense APM training regiment that the pros undergo.

APM is a huge indicator of Starcraft "skill". Its not the only thing of course, but winning "micro-battles" greatly changes the game.

I don't care how good Michael Jordan is. He'll never "win" a game of basketball vs a standard professional by shouting commands to an average joe.

Similarly, no average joe will be able to perform a muta-harass while retaining full-speed, taking only a single missile from a Turret. That sort of "micro-skill" takes practice and dexterity.

⬐ derefr

You don't think it'd be interesting to take a player who's already one of the top players, and measure the marginal gains of them doing their own macro+micro, vs. just doing micro and leaving macro to the AI?

⬐ ktRolster

We can see that now, with the new Archon mode, which allows two players to control the units together.

⬐ garrettgrimsley

I haven't been following SC2 since HOTS, are they really still trying to achieve feature parity with Brood War?

http://starcraft.wikia.com/wiki/Team_Melee

⬐ ktRolster

I haven't been following SC2 since HOTS

Too bad, it's really good.

The obvious problem is that speed of tactical execution can make up for a lot of strategic thought. The famous example: you can rush a line of siege tanks with zerglings if you can micro them fast enough[0].

[0]:https://www.youtube.com/watch?v=IKVFZ28ybQs

⬐ LockeWatts

I hope that in the interest of fair play they'll limit their AI to 300 APM or so. Make it win not on mechanical execution, but on decision making.

⬐ cm2012

Even with that though, They say Starcraft is still 5-10 years out for AI to beat pros: http://www.newyorker.com/tech/elements/deepmind-artificial-i... (ctrl+f for Starcraft at the bottom of this article) -----