Active Exploration for Learning a Symbolic Representation
garrett at cs.duke.edu
||Friday, November 18, 2016
||1:00pm - 3:00pm
||D344 LSRC, Duke
We introduce an active exploration algorithm for efficiently learning an abstract symbolic model of an environment. We show that it outperforms random and greedy exploration policies on an Asteroids-inspired computer game domain.
Advisor(s): Ron Parr and George Konidaris
Committee: Carlo Tomasi, Kris Hauser