Hacker News new | comments | show | ask | jobs | submit login

It's not 'AI' (what actually is?), but mostly hand-crafted state-machines trying to achieve game-specific goals, which directly inspect the current game state instead of trying to build their own 'world model' (of course with restrictions like fog-of-war, visibility-checks and so on so that the cheating isn't too obvious).

Really no that much different from what the Pacman ghosts did, just developed further from there (especially during the Golden Age of strategy games during the late 90's and early 00's).

With this base, scalability is achieved through fairly traditional performance optimizations (mostly using the right algorithms and data layout, especially for path-finding and 'visibility checks').

Also in strategy games, AI is often layered like a military chain of command, where the "commander AI" only makes high level strategic decisions and only has a very 'sparse' world model, while the lowest level 'soldier' AIs are mostly occupied with pathfinding but only know about their immediate surroundings.

Also, each game genre has their own highly specialised, hand-crafted "AI" algorithms. A first-person-shooter AI is completely different from a car-racing-game or realtime-strategy game.

Exactly this. It's also worth mentioning that 'true AI' would be an absolute nightmare in terms of delivering a game, the QA testing burden would be so enormous for any reasonably large game that it'd be difficult to get it out the door.

I remember working at a games studio years ago and a kid straight out of university joined us after doing a degree in AI - assuming that games used real AI. Nope, it's all smoke and mirrors.

> It's also worth mentioning that 'true AI' would be an absolute nightmare in terms of delivering a game

An important sentiment I've heard many times on the gamedev.net forums is that machine learning techniques are usually too difficult to tune in order to make the agents behave in the way that the designer wants.

Game AI is about providing an illusion of intelligence and about providing a designer-crafted experience to the player. So it often makes sense to cheat in order to achieve this.

Having said that, some games really do benefit from smarter AI. For example, real time strategy games sometimes do (eg Supreme Commander AI mods, AI War Fleet Command etc) and often first person shooter bots as typical dumb bots are simply not as fun to play against than real humans, although you mostly want the bots to have some high level tactics ability (not perfect aim or such), which is why the game FEAR is often applauded for having fantastic AI (it uses Goal Oriented Action Planning to produce high level tactics such as flanking). But most games don't go very far at all.

No one has managed to create a real AI (as in strong AI). Machine learning, deep learning is smoke and mirrors too.

...and in games, you actually want smoke and mirrors:


If you really had hard and strong AI, a lot of games certainly wouldn't be as much fun to play anymore for casual players (spare some games you want to be frustrating). You want the protagonist to eventually conquer the enemies and win.

This might be true for FPS and other genres where reflex and speed are the most important factors. However most competitive strategy games will definitely benefit from strong intelligent AIs. For example in Age of Empires, the problem isn't that the AI is too strong (they're not - with enough practice anyone can beat the hardest AI). The problem is that they don't play like a human would, and are exploitable with certain strategies which even a beginner player wouldn't fall for.

Yup. Imagine a boss in a game decides it's not in his best interest to be predictable, or take matters in his own hands and attack the players when they aren't ready. Or any number of things that sounds cool on paper, but would be exceedingly frustrating when actually playing the game.

Imagine a boss in a game tired of fighting every day, and just giving up and not fighting back.

That's essentially the plot of Wreck-It Ralph.

I think louthy means something that works more like an agent observing it's environment,learning, strategy etc,

Most entities in games are more like a wall following robot.

Can you expand on this comment? Is there an industry standard definition of real AI? I'm genuinely curious.

Industry standard usually means content-free marketing stuff.

Strong AI is a relatively well estabilished term of art in the field of AI: https://en.wikipedia.org/wiki/Chinese_room#Strong_AI

There's a lot of things hyped/marketed as "AI" that are merely algorithms or applied statistics on large datasets. Things that totally miss the mark on the computer science aspects of what AI is suppose to be.

I'm glad someone referenced the classic AI of a PacMan Ghost ;) Id's Doom from the early 1990s is another deceptively simple yet surprisingly engaging instance:


An agent's set of possible actions is conditioned on its environment, other NPCs as well as the players actions. Even for a finite number of variables you can quickly see how the problem becomes computationally expensive for a single agent.

You want to to build unsharded persistent worlds with complex character behaviours and allow millions of online simultaneous players all sharing the same game state? Then you need to take a page from architects building scalable cloud computing infrastructure and applications that serve billions of request per second with low latency.

Companies like improbable.io are abstracting game state and logic with SpatialOS. But I think there is still a lot of room here for some startup to combine "Unreal Engine + AWS". Creating a true "cloud native game engine". Even if its just HTML5 based and targeting games such as Slither.io.

Quest - An iOS "io" Game from Improbable


Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact