Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Beyond Markov Decision Processes for Stochastic Planning

MausamUniversity of Washington[Home Page]

Notice:  hosted by Karen Myers

Date:  2007-04-04 at 11:00

Location:  EJ228  (Directions)

   Abstract

Controlling intelligent agents in complex real-world environments poses requirements that are not addressed in classical planning formulations. Such problems typically involve ability to reason with uncertain action effects and are frequently modeled as Markov Decision Processes (MDPs). Recently good progress has been made in solving MDPs; however they make many unrealistic assumptions, for example, instantaneous actions, no concurrency, and discrete state spaces. These assumptions make it impossible to formulate many real problems in this model. In this talk I describe our approaches to model concurrent, durative actions in an MDP framework. I present several techniques that span the spectrum from optimal algorithms to fast approximations. Our methods inherit the advantages of both decision theory and heuristic search. I also briefly describe our results on planning with both discrete and continuous variables as well as a general idea of algorithm hybridization to speed up policy construction in many planning and search problems.

   Bio for Mausam

Mausam is a Ph.D. student at the University of Washington who expects to complete his degree in 2007. His main research interests are algorithms for automated decision making, machine learning, heuristic search, and probabilistic reasoning. In the past, he has also worked on cache-performance of algorithms.

   Note for Visitors to SRI

Please arrive at least 10 minutes early in order to sign in and be escorted to the conference room. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the visitors lot in front of Building E, and should follow the instructions by the lobby phone to be escorted to the meeting room. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page.

SRI International
©2014 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy