Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepMind Can Now Beat Us at Multiplayer Games, Too

nytimes.com

Post reply on HN
Print view View original

21–26 of 26 posts

Re: DeepMind Can Now Beat Us at Multiplayer Games, Too

#21

Post by Zenst »

781 wrote: post #19
Zenst wrote: post #17

A benchmark for me would be a game that can handle a MMOPG like eve-online. What with certain tactics in game valid - like griefing, spies etc. An AI can handle that would be not only impressive, but learn a set of skills that many would feel uncomfortable about being within the realms of AI. After all, humans cheat, would we want that allowed by an AI. Equally an AI could stumble upon an exploit in a game and not re…

> A benchmark for me would be a game that can handle a MMOPG like eve-online I don't think they managed to connect Excel to their game environments yet.

MMOPG's are not all reducible into an Excel spreadsheet and the part were I said "What with certain tactics in game valid - like griefing, spies etc. An AI can handle that would be not only impressive, but learn a set of skills that many would feel uncomfortable about being within the realms of AI." was the part I was discussing.

Re: DeepMind Can Now Beat Us at Multiplayer Games, Too

#23

Post by Zenst »

gameoflife wrote: post #5

People mentioned in the article seem to doubt about applicability in the real world. If nothing else, I think it brings video game development closer to being an automated process. A game could simulate various conditions and design an infinite number of complex environments. Am I way off?

I would see this being used more for automating many aspects of testing games, then down the line - level design. But for automating game development, you would require creativity - unless you're into sudoku style games.

Re: DeepMind Can Now Beat Us at Multiplayer Games, Too

#24

Post by mark_l_watson »

While I am a fan of DeepMind’s research (Alpha Go and Alpha Zero blew me away - I wrote a commercial Go program in the late 1970s for the Apple II so I appreciate the problem, and I used to work with DeepMind cofounder Shane Legg at Webmind), respectfully, I do have a criticism:

I would like to see them use their talent and financial backing from Alphabet to tackle the hard problems of common sense in AI and in general the science of what it will take to reach AGI.

Deep learning is brittle, as can be seen in the good science of finding adversarial attacks on trained models. I would like to see less accuracy on dev and test sets, smaller more general models, and especially not see convolutional models as the basis for vision systems in self driving cars. My intuition is that discarding information of relative positions and relative relationships of large features in an image is a bad idea for the self driving car problem.

They have really pushed progress for an old technology (reinforcement learning) and achieved fantastic results but in my experience if there are not many failures along the way, then perhaps goals are not being set high enough.

Post reply on HN