AI-Vision-Robotics Division Colloquium

and

Seminar on Computational Learning and Adaptation



 
Remembrance of Things Past
 
Leslie Pack Kaelbling
Computer Science Department
Brown University
Providence, RI 02912
lpk@cs.brown.edu
 
 
Behaving effectively in partially observable environments requires remembering something about the past.  Partially bservable Markov decision processes (POMDPs) provide a formal model for describing and evaluating control problems that require memory.  An agent in an unknown POMDP has two main strategies:  learn a model of the POMDP, then solve for a good policy or learn a policy directly.

I will begin by describing an algorithm for learning POMDP models for robot navigation, which, coupled with previous work on controlling POMDPs, yields a behavior learning system.  Then, I'll talk about some very recent work on direct approaches to learning policies for POMDPs without first learning a model.  I'll conclude with a description of a new project on learning models for visual navigation in humans and robots.
 


Date: Thurs., March 4
Time: 4:15pm
Place: Gates 104

Return to the seminar schedule