Post by KostaAndreadis @ 02:16pm 20/07/21 | 0 Comments
Enemy AI can often be so scripted that it's obvious to the point where a pattern is instantly recognised. Sometimes it takes time to learn the right moments to strike, shoot, or find an opening. Either way AI as we know it in games, that being those of NPCs and bosses, are built on scripts and code hard-wired in game data. Tony Tamasi, Senior Vice President of Tech Marketing at NVIDIA, believes that true AI integration will open the door to an exciting future.
"If you think about AI being ‘Software 2.0’ it just seems natural that people are going to find applications for this in real-time gaming. DLSS is really the tip of the spear, so to speak, for that," Tony Tamasi tells us. "It's probably the first interesting application of neural networks for real-time graphics."
And with that NVIDIA DLSS utilises the AI-based Tensor Cores inside the GeForce RTX range of graphics cards to boost both resolution and performance - with the outcome looking like some sort of magic trick. In that the image quality doesn't suffer in the process.
Its recent addition to Red Dead Redemption 2, as per below, shows some of that magic in action. Courtesy of the old west.
But with Tensor Cores used for impressive rendering, could neural networks and AI hardware in the GeForce RTX range be used for gameplay?
“AI is going to kind of unleash a whole new generation of advances, some of them we haven't even thought about yet,” Tony says. “I'm kind of looking forward to the next phase where you start to see AI brought into games where they can impact gameplay. Games have had AI for a while in the sense that they've had scripted behaviour for NPCs. That’s still hand-coded behaviour, if you attack me, I attack you back. What if a boss learned? What if characters had behaviours that changed? What if a boss fight wasn’t this carefully scripted dance, but rather the boss learns how to fight the player based on their attacks.”
"You would create a whole new generation or class of games, stuff that we can't even really envision really," Tony adds. "Games that were truly dynamic and truly alive. Of course, that would require changes in the way we build games, engines, and even how we approach game design. But the capability for that, the groundwork, has been laid. And that’s exciting."
Another example could be in an RPG, where NPC reactions to decisions are true AI-based and not a binary "Person X Liked That" response. More how they feel about it based on everything they know and have seen. This could extend to factions, and a dynamic world where who might be in control of one region is the outcome from player decisions made earlier and neural network learning around abilities and skills. It's truly fascinating, and something that doesn't sound all that far off.