but It was not a reaction to "oh no my cutoff is gone, I must take It" It was a just another simple battle for AI. If that was important It wouldnt loose the first place or go straight as an arrow.
HOI4 AI status
- Thread starter ruzen
- Start date
-
We have updated our Community Code of Conduct. Please read through the new rules for the forum that are an integral part of Paradox Interactive’s User Agreement.
We love and believe in you!Nice thread with good points. I am happy to see some attention on the AI
While I am not willing to go into details about the state of the AI right now, rest assured the work on it continues and I hope to spend a lot of time even beyond release to refine it.
- 1
in an earlier situation where daniel managed to nearly encirlce 4 or 5 chinese divisions and he gave the order to cut them off, they instantly retreated instead of the one that was busy in an fight and couldnt. All of them except the 1 that didnt managed to retreat. Of course there will be situations in the game, especially in the current state where there might be some hick ups. Overall, if the game would be perfect right now they wouldnt hold it back for another 2 months.
Especially for an game that has such an complexity, the AI devs did an incredible job so far.
Last edited:
- 5
What I would really like to see though, is a hands off AI vs AI game. Its good that an AI can give a human a challenge but what I feel is more important is how the AI of a weaker country or army will react to and counter the AI of a superior nation/army (aka fight for time, defense in depth or just fighting retreat). If it gets steamrolled like unmodded HOI 3, that might be a problem for a long game.
- 3
i am so excited for the game seeing the AI improve over HOI3. if they can fight a defense in depth the eastern front is going to be incredibly tense. Not to mention this version of HOI seems to have upped the ante on supply issues, making fighting in china get properly bogged down as you'd expect it to and also daniel stated he got lucky in his WWW invasion of russia (managing to seize control of states supply and resource generation just as his supplies were running out each time).
seeing as that WWW was super early state of the AI compared to now where inferior chinese divisions with worse equipment, org, and i believe each division is smaller than a japanese division are threatening breakthroughs and encirclements, imagine the eastern front with afully powered up army without trotsky reducing the number of factories immensely! (also in WWW factory build up was incredibly easy as civilian factories were cheap as chips so human players were spamming factories like crazy)
i'm also really looking forward to seeing how the china situation develops. if the chinese AI can hold off daniel, i think its safe to say it can hold off any of us as daniel has more hours in HOI4 than there are hours until the release date...
seeing as that WWW was super early state of the AI compared to now where inferior chinese divisions with worse equipment, org, and i believe each division is smaller than a japanese division are threatening breakthroughs and encirclements, imagine the eastern front with afully powered up army without trotsky reducing the number of factories immensely! (also in WWW factory build up was incredibly easy as civilian factories were cheap as chips so human players were spamming factories like crazy)
i'm also really looking forward to seeing how the china situation develops. if the chinese AI can hold off daniel, i think its safe to say it can hold off any of us as daniel has more hours in HOI4 than there are hours until the release date...
- 1
The Chinese encirclement of the Japanese that happened in the south of this area, was a direct result of the troops responding to this crisis being pulled from the front line, China still lost a lot more men, but japan lost more than 200% more men in that encirclement than they had in the entire invasion up to that point.
Japanese troop losses were 11k when checked(30 minute mark), and went up to 26K before end of scenario with troops still cutoff in that Pocket (46:47 into the video) .
Chinese losses were a combined 401K, and went up to 555K
the end result of the evolution still wasn't good for china, but it was the least bad result they've had so far
Japanese troop losses were 11k when checked(30 minute mark), and went up to 26K before end of scenario with troops still cutoff in that Pocket (46:47 into the video) .
Chinese losses were a combined 401K, and went up to 555K
the end result of the evolution still wasn't good for china, but it was the least bad result they've had so far
I do wish people would take into account that herr Daniel is considered a genuine tactical mastermind with borderline cocaine-enhanced reaction speeds when criticizing HOI4's AI.
Not to mention the fact he's fighting with optimum troop/general composition against an inferior, vastly under-equipped enemy army that's having to operate within severe supply constraints.
Not to mention the fact he's fighting with optimum troop/general composition against an inferior, vastly under-equipped enemy army that's having to operate within severe supply constraints.
Last edited:
- 4
- 2
Actually seen the WWW now, and thought the AI was more than respectable (particularly as it's still a work-in-progress, but the AI we saw in the vid would be a substantial step forward over HoI3 (and leagues ahead of HoI1 or 2) as it stands). I'd argue China was perhaps a little to 'push forward and sod the consequences'-happy when it made a breakthrough, but if we're saying "perhaps it was a little", then the AI is very good indeed compared with past iterations. China seemed to be using its airforce sensibly as well, from what we could see.
If this was HoI3 we'd have been watching half the Chinese army marching back and forth along the frontline redistributing for the last year (something we've seen very little of, as far as I can tell).
If this was HoI3 we'd have been watching half the Chinese army marching back and forth along the frontline redistributing for the last year (something we've seen very little of, as far as I can tell).
- 5
I'm most pleased that it looks like the devs are giving proper resources to AI.
Plausible, problem causing AI will be much appreciated guys.
Plausible, problem causing AI will be much appreciated guys.
- 1
A huge plus one to this. AI is the reason I've stopped (mostly) playing past HoIs, and the reason I keep playing EU4 (the AI in EU4 is a substantial step up from the past, and continues to improve).
IMO quite the contrary, he stated over and over again that he can´t have more troops in the north because of the supply/infrastructure situation. It is more or less a stalemate situation or a slow crawl atm.
To open up additional fronts in the south ( well supplied by ports ) is the right thing to do because it takes pressure from the north and forces the chinese to at least garrison 3+ provinces surrounding each lost ports. The japanese are strong enough to force and defend each landing ( unfortunately also because AI doesnt garrison ports well ) and have undisputed naval supremacy and thus maximum supply. This is comparable to the european theatre when the "second front" was opened.
As soon as he takes every port on the chinese soil he may gain the upper hand in the chinese theatre.
This is great to see, and now it gets me wondering if the AI will still go for broad fronts or specifically aim to encircle. That's one thing that bothered me, AI wildly attacked with a "fuck it, general offensive" and not a calculated encirclement to starve me of forces. It would be great to see this in the AI.
The best Ai is simply to copy human strategies. I've always liked Forza's Ai system where it mines player data in order to present a Ai strategy in a race. Totally different. But I generally think the best route is to learn and preform how a player does. Instead of having it think on it's own. For example one of the biggest issues is AI thinks 1 2. Not 1 2 3 4 5 6 7. Learning from Chess computer programs might be useful. I just know when fighting against the Ai it's easy to do tons of tactics that the Ai never defends. Tons of them. I hope it's changed. But I'm skeptical. I haven't seen somebody mirco everything versus the Ai on its own.
- 1
As awesome as that would be, it simply is not technically feasible for a game like HoI. As a comparison, consider the recent successes of googles deep neural network tech defeating champions at Go.
Go is significantly more complex than chess because of the much larger number of possible moves per turn. While chess AI gained success by calculating future possible board configurations and attempting to steer the game in a beneficial direction through this search tree, Go just has too many possible board configurations to do that (significantly more than the number of atoms in the known universe).
Google essentially used a supercomputer and a ridiculous ammount of training data (aside from letting it play against itself) to accomplish this feat.
While Go has 361 positions HoI 4 has over 13000 provinces. The number of possible states of each one of the 361 positions in Go is 3. The number of possible states of a province in HoI4 is hard to quantify with a discreet number. And apart from provinces there are multiple off map systems and partially off map systems.
On top of that Go is a turn based game where the AI can take time to process each move. HoI4 is pausable real time. Even if you consider each hour a turn, there are still expectations on the AI not taking several seconds, let alone minutes, to process what it is doing (which can be any number of things as part of the same tick.)
The math on this just explodes.
Frankly, as I write this I am amazed at the level we have managed to get to already with the HoI4 AI.
Trust me; when or if the time comes that this is a viable approach I will enjoy looking into it even if I have to use my free time to do it
- 26
- 20
- 1
My greatest AI concern is about naval invasion. The AI of HoI3 was particularly bad at this (I saw once UK landing troops in Netherlands, but without any support nor reinforcement so Germany pushed back this attack easily), and it was a big mess for the game as it means Japan and USA were basically stucked in "sitzkrieg". Why ? I don't know, but I think it's maybe due to the difficulty of the naval transport system. If this problem doesn't exist anymore in HoI4, you'll make me happy.
Suggesting that we use recorded learning for a complex strategy game AI because it works in chess/racing is basically like suggesting that you solve a broken spine with massage because it works for back aches. The scope of the problem is simply so far beyond the solution that the solution ceases being applicable.
- 23
- 8
- 2
Does the AI need refining? Sure. Is it better than HOI3? Yes!
I can already see that I'm not going to get bored playing this game, which is all I really want out of a game.
I can already see that I'm not going to get bored playing this game, which is all I really want out of a game.