AI Development Discussion and Feedback


  • Admin

    @Quorthon4 That mostly just looks like bad luck as between Austria and Ottomans they should have killed on average at least 5 more units than they did. And then Germany would have had a strong attack opportunity.



  • @redrum Ok, so here are numbers I get with combat simulator (2000 simulation count):
    Austria expected TUV swing: -49.62
    Ottomans expected TUV swing: -17.22
    on average both attacks should kill roughly 10 russian infantry

    German potential attack without the strafing attacks above expected TUV swing: -26.54
    German potential attack with 10 less russian infantry to defend: 32.3
    Total benefit from strafing attacks: -49.62 - 17.22 + (32.3 - (-26.54)) = -8 TUV swing


  • Admin

    @Quorthon4 Right but then Germany on average would get something like ~30 TUV swing and gain the factory. And ideally, you don't need to Ottoman attack. So its really -50TUV for Austria for 30 TUV for Germany plus they gain the factory.

    I think its pretty close with average rolls. I don't think its a terrible gamble on strafing.



  • @redrum fair enough, there's also strafing attacks against same area round 8


  • Admin

    @Quorthon4 Yeah, looks reasonable as again Austria gets poor luck though Germany is still able to at least take the factory.



  • @redrum assuming you value the factory that high, then yes. but I don't think it's worth ~ -27 TUV turn 5 or -60 TUV turn 8 to take the factory.


  • Admin

    @Quorthon4 Yeah, maybe the AI overvalues the factory a bit. Though the turn 8 would be -60 then +30 so only -30 total on average to take the factory.



  • @redrum yeah, sorry, it's like you said closer to -30. Then you probably should compare that to the other attacks that wasn't made that could have potentially had positive TUV.


  • Admin

    @Quorthon4 Yeah, these are both close calls on whether its worth it especially when you look at potentially what they could have gained otherwise. But I don't think either of them is terrible either. There is a pretty significant amount of randomness as well in the AI where they might choose other options if you replay the same game on those turns.



  • @redrum Thanks for the response, I overwrite save games as I play them, but I'll start trying to keep track of examples.



  • @redrum Also, I agree there is no "golden ratio" for any map/player/etc, but for any map/side/situation (of the maps I've played), the bigger the stack, the more it benefits from having a diversity of units. I agree someone would argue 15/4/2/2 vs 20/4/2/2 til they're blue in the face, but either of those armies will beat 25/0/0/0 every time.


  • Admin

    @luhhlz Agree. The AI tries to buy a variety of units and tries to categorize them into types like fodder vs defensive vs offensive vs multi-move. It then uses these categories and checks the situation around a factory like whether its threatened or how far from the front it is to balance weights across these. Then it weights the units within each category (so infantry in NWO have a very high weight in the fodder category) and randomly selects units based on these weights.

    So for say a factory near the front the AI on NWO will try to buy some fodder (usually infantry) and some defensive/offensive units (elite, artillery, etc) to give more strength. For factories further from the front, you'll see it buy more tanks, mech inf, mot inf, as it wants higher move units.

    Trying to determine how much of each category and how to weight units within each category is tough as maps can have very different unit sets. The above is also somewhat simplified as there are a bunch of other factors as well but those are kind of the core factors.



  • In the enthusiasm for news of new tripleA WW1 map stuff, I've been watching the AI try to stalemate itself in that old Great War map I made with Surtur ages ago hehe. Currently skynet has bloodied itself into the 10th round. Going to just let it go tonight till it breaks itself or my memory. So far the HardAI seems to be managing fairly well for itself on either side. A dose of nostalgia from an oldy. For all its idiosyncrasies, it was fun map for the time, trying to bend the engine in early days hehe. But I haven't actually opened it up since 4.0, and now the AI is much much improved from back then.

    Its been fun to watch the machine actually cobble together a vague kind of plan, compared to the nuts ass stuff it used to do with the AI when this map was first made like 10 years ago hehe. Cool to have an AI that gets the job done, pretty damn well actually, with something based on the old v2 rules.

    CP are finally pushing where they can, but Allies just saw the US hop into the mix, so still a nail biter over here lol. I don't think the boys'll be home by Christmas this year. Nice work Hard AI

    Great War Hard AI round 10.tsvg

    Getting my kicks off for the era, watching the AI lamp itself before I crash into bed hehe. But will dream of badass 1914 PvP stuff to come for sure.

    night all


  • Admin

    @Black_Elk Yeah, I did some very limited testing on Great War with the AI a while back. It does alright as for the most part the rules of the map are very similar to revised. The only weird part is the USA maze to enter the war. But the AI eventually gets through that probably just a few turns slower than most human players.

    And since the AI doesn't care about the cut outs, in some ways it has an advantage over newer players that tend to struggle with those.



  • Yeah the various colonial boxes and naval abstractions were probably a bridge too far I think, though I still kind of like the western front box as a novel way to make the fighting in France and Belgium feel more thematic and engrossing, given the limitations of the time. One thing that the map failed to resolve, similar to many WWII maps is the overall advantage of attacking G directly via amphibious into Hanover or a Baltic push. I guess a simple solution might have been like some impassible sz to block the approach at the danish straits, but didn't really have an easy way to do it without cutting G off from the water. US entry can get pretty gamey when they arrive in force and start getting the dead drop on G amphibious. In that way it's still falls into a revised WWII trap of sorts, but still pretty Russia centric for the most part. The AI exploits that to good effect, as I imagine most humans would too, even if it takes a little longer to get there. CP AI finally handled the East after several more rounds, though the AI Allies are trying their best to push across Italy with US now. All in all the AI does its thing pretty well here on balance. What they got going with the Turks, nobodies business haha.

    Great War Hard AI round 23.tsvg


  • Admin

    @Black_Elk Yeah, especially in WWI, amphibious assaults were near impossible at any decent size scale. Even in most of the WWII maps we have, amphibious assaults are way too easy. I'm hoping to better capture this fact in the new WWI map that we are working on.


  • Moderators

    I suppose it is well known that the AI is very bad at protecting the "combat infrastructures" (meaning infrastructures able to do something in battle), both mobile and not mobile ones, but I want to show this off as an extreme case, the AI leaving, for absolutely no reasons, a stack of 3 mammoth alone for the taking, while having several combat units that could have easily protected them.
    20190527_02.png


  • Admin

    @Cernel Mind adding the save game as well?


  • Moderators

    @redrum Ok, I'll post it once the game ends (likely by surrender). Btw, I'm playing it in the lobby now (so, anyone can join it).


  • Admin

    @Cernel I did a quick test with the latest pre-release setting up a similar scenario and I believe this is already fixed. I made some improvements when we were doing some Dragon War testing that I think now handles the isInfra land units better.


Log in to reply