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.
The first part is embodied intelligence which is where robotics still struggles especially end to end control. The actuation part is still mostly based on control/optimisation theory rather than learning
Atari joystick doesn't need 10 fingers to play. 
pic.twitter.com/Yt29sHvKSn
Good food for thought, but I disagree. Mental models is only one part (vide Go, where it is easy to abstract board & stones). And even for mental models humans are well below 100% (is it a platform or just backround? is it a powerup? can I kill this enemy by jumping on it?).
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
