Most events on this list can be tied to a specific page somewhere on the internet.  List entries contain links to such pages through the "Details".   Occasionally events have no such page or the information on it is inadequate.  In such cases I attempt to cobble together a details page myself.

Hi all,
Pedro Tsividis will be presenting at ML Tea next Monday (?12/12?; talk details below).

As usual, drinks and snacks will be served.

Hope to see you there!

- ?Jonathan


Title: Toward human-level learning of Atari games
Date: Monday, November 28, 2016
Time: 4:30 to 5:00 PM
Location: G4 lounge (32-G475A)


Atari games are an excellent testbed for studying intelligent behavior, as they offer a range of tasks that differ widely in their visual representation, game dynamics, and goals presented to an agent. The last two years have seen a spate of research into artificial agents that use a single algorithm to learn to play these games. The best of these artificial agents perform at better-than-human levels on most games, but require dozens or hundreds of hours of game-play experience to produce such behavior. Humans, on the other hand, can learn to perform well on these tasks in a matter of minutes. I will present data on human learning trajectories for several Atari games and test several hypotheses about the mechanisms that lead to such rapid learning.

Thanks to our sponsor: ML Tea refreshments are provided by FeatureX, a machine learning startup in Kendall Sq. http://www.featurex.ai