You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
"Human performance" on Atari games isn't how well a human can play with their own 10 fingers. It's how well the abstract mental models of the game inferred by the average human can perform when coded up into a simple program. That means perfect scores for most games.
And the data-efficiency of that process is staggering -- a human only needs a handful of games to come up with mental abstractions enabling it to programmatically solve most of these games at 100%. That's what the bar is. That's what we should aim for.
Don't let them tell you that deep learning has achieved "superhuman" performance at any of these games -- any random programmer can come up with a better solution program for a given game in an afternoon. That's what human-level means.
If you remove human visual affordances, then the human's performance sinks like a rock. https://openreview.net/pdf?id=Hk91SGWR- …
Sample complexity is a serious issue. But I'm not sure your remark is fair. What counts as "data" for a human? Gaming happens after years of cognitive development. While AI is far from being able to do that, the data argument itself is still tenuous for that reason.
In most cases, we are training "newborn bot" from scratch. To be fair to the "bot" you should also unlearn any game played by the human ever and probably also any visual concept that support game logic understanding...
Or you have to count the 24 images/sec during wake time as "pre training" data for the human ;-)
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
