If you end up blocked by a popup blocker, or just don't feel like reading fluff, or like me you've got the browser locked down too tightly for their integrated video player to work, the paper is at <a href="https://arxiv.org/pdf/1606.01868v1.pdf" rel="nofollow">https://arxiv.org/pdf/1606.01868v1.pdf</a> and the video mentioned is (probably, since I didn't see the original) at <a href="https://www.youtube.com/watch?v=0yI2wJ6F8r0" rel="nofollow">https://www.youtube.com/watch?v=0yI2wJ6F8r0</a> .
I look forward to the day when you are taunted on the Starcraft boards for playing "like an AI" :-)<p>That said, game theory has always been an excellent way to analyze AI systems. And using "modern" games (which generally provide attractive skins over a classic mechanic) certainly makes it easier to watch/sit through. When DeepMind starts beating people playing Diplomacy then we'll know we're in a whole new game.
This is interesting but it's still far from how a human would learn how to play the game. Humans don't have inbuilt rewards for Montezuma's Revenge, they acquire them culturally. How much of what was learned (by the machine, not the researchers) in playing Montezuma's Revenge could be applied to a game like Zelda? A human would instantly notice many of the connections between the two games: enemies that follow simple patterns and harm the player on contact, rooms that connect to one another laid out on a grid pattern, single use consumable keys that open doors, valuable gems to collect. Is the machine able to make any of these connections on its own?
On behalf of all who have "played" Montezuma's Revenge for real, let me say we look forward to the day when it can be outsourced to the Cloud.<p><a href="https://en.wikipedia.org/wiki/Montezuma%27s_Revenge" rel="nofollow">https://en.wikipedia.org/wiki/Montezuma%27s_Revenge</a>
It might be a interesting future if computers become powerful enough to be able to run this kind of IA. Then games companies might be able to use directly a generic IA like this instead of developing specific ones. But I suppose it will be hard to do and won't happen (if it does) before a long time.
So lets say I take the trained network, and flip the color of the pixels, and make some other cosmetic changes (keeping the game intact). Will the network then solve it in the first try?
I'm confused by the subtitle of the linked article, which says "The AI system was able to solve the complex game in just four tries". But the video shows the AI dying many more times than that, and not ultimately winning the game, just learning to explore a portion of it successfully.<p>What did the Wired editor mean by "solve" and "four tries"? (Or, for that matter, "complete"?)
The text of the article is cut in half for me. Can anyone else confirm the same rendering behavior?<p><a href="http://i.imgur.com/FfcXAmi.png" rel="nofollow">http://i.imgur.com/FfcXAmi.png</a><p>I am on Windows 7 using Chrome 51.0.2704.79 m and the text issue occurs in incognito mode as well.