Where is the 'Unbeatable' AI effort now? What happened, Adam Isgreen?

I remember reading this interview way back, with World’s Edge creative director Adam Isgreen and Relic game director Quinn Duffy:
[Age Of Empires 4 Will Eventually Have An AI That You Will Never Beat]

In a new interview with World’s Edge franchise creative director Adam Isgreen and Relic game director Quinn Duffy, I asked the pair about an age-old annoyance: AI. When you up the difficulty to get a real challenge, the dev answer has simply been to let the AI cheat — or give them absurd buffs to resources and other tricks to paper over the cracks of the AI not being smart enough.

Age of Empires 4, gracefully, won’t resort to either of those old-school methods. But Isgreen and Duffy both revealed that Age of Empires 4 has been toying around the idea of a Merciless AI. It’s inspired by some of the work that went into *Killer Instinct’*s Shadow AI, [which learnt from the moves players made].

“We use machine learning in training the AI right now, but we want to take that even further. Down the road, not at launch, we’ll probably look into having a merciless AI that keeps learning the more people play against it, to the point that it’ll be unbeatable,” Isgreen said. “But we’re OK with that, because if you opt into that difficulty, if you want to opt into making the AI better at beating you, go right ahead.”

So what happened, Adam Isgreen? How did these bold, exciting claims materialize into the AI we have today?

How do we reconcile the recent 2x resource gathering rate added to the Hardest AI, with the claim in this interview that the AI wouldn’t resort to “cheats”?

I’d love to know about the progress with the learning AI that was mentioned in the interview. I feel that’s what many CPU and co-op AOE4 players would want to see. An ‘unbeatable’ self-learning AI would be amazing, and make for a great competitive advantage to AOE4 over other RTS in the market. And it seems like it’d be a TRUE improvement to the AI - unlike 2x gathering rates and cheats. Is this effort still happening?

Thanks for checking.


Look for a collaborative game against the AI and I bet it will take hours without finding one, which is why it’s important to keep the ladder healthy in multiplayer, between people, and that is done by working on other community demands that are more important than the AI. Many already asked to add it in another difficulty, end of the topic, thanks

1 Like

Turns out coding AI is hard, especially when you are trying to make it compete with highly efficient build orders.

1 Like