News for hackers. Stuff that matters.
Re:Deep learning is hitting a wall? by 29athrowaway on Wednesday March 09, 2022 @11:41PM (#30623284)
DeepMind managed to rekt the best players in Go and StarCraft after a few years of founding. Go has been played for 3000 years, and it has influenced military strategy since ancient times. The strategies you can find in Sun Tzu's Art of War were influenced by the game of Go.

Did you know what is the difference between the military simulators used by defense departments and strategy games like Go? Did you know both share a lot in common? What you dismiss as "game playing" has more present applications than you imagine and will make the difference between life and death in armed conflicts.

The orders given by generals will likely come from a successor of MuZero. And that may expand to every key decision making process, like the equipment to be manufactured, logistics, etc.

Combine that with the power asymmetry coming from drones and that "game playing" will become the most dominant force in this world.

Re:Deep learning is hitting a wall? by 9wzYQbTYsAIc on Wednesday March 09, 2022 @11:50PM (#30623340)
Has anyone pit DeepMind against a constraint satisfaction algorithm in StarCraft? I’ve heard constraint satisfaction can be good enough to simulate playing StarCraft.
Re:Deep learning is hitting a wall? by 29athrowaway on Thursday March 10, 2022 @02:10AM (#30623952)
StarCraft is not a complete information game. There's a fog of war.

There's much that can be done to trick the opponent into making incorrect assumptions.

Re:Deep learning is hitting a wall? by 9wzYQbTYsAIc on Thursday March 10, 2022 @12:25PM (#30629574)
I think StarCraft I has a way to turn off fog of war.
Re:Deep learning is hitting a wall? by 29athrowaway on Thursday March 10, 2022 @02:02PM (#30630986)
Not in multiplayer games as far as I know.
Re:Deep learning is hitting a wall? by 9wzYQbTYsAIc on Thursday March 10, 2022 @03:24PM (#30631948)
No, but for AI testing purposes it can be done.
Re:Deep learning is hitting a wall? by ShamelessC on Thursday March 10, 2022 @08:25PM (#30635039)
That would defeat the purpose of solving an incomplete information game.
Re:Deep learning is hitting a wall? by 9wzYQbTYsAIc on Thursday March 10, 2022 @08:49PM (#30635174)
But it would be neat for testing out ideas in games with perfect information.

I know next to nothing about game theory, but aren’t games with perfect information what would generally be considered “fair”?