POMDP Symposium Participant Page

• Michael Littman (Duke). Primary interests: mathematical and algorithmic foundations, factored models, robotic applications. Presenting: POMDP overview
• Tony Cassandra (MCC). Primary interests: mathematical and algorithmic foundations, approximations and heuristics. Presenting: something organizational.
• Sridhar Mahadevan (MSU). Primary interests: reinforcement learning, robotic applications. Presenting: new POSMDP results with a real robot. [coming late Friday.] Also, new data relating POMDPs to animal behavior!
• Steve Kemp, Dave Eckerman (UNC). Primary interests: reinforcement learning, other applications. Presenting: POMDPs as a model of learning agents in psychology.
• Satinder Singh (AT&T). Primary interests: reinforcement learning. Presenting: Something cool.
• Nevin Zhang, Weihong Zhang (HK UST). Primary interests: mathematical and algorithmic foundations, approximations and heuristics. Presenting: Overview of exact methods.
• Craig Boutilier (UBC). Primary interests: factored models. Presenting: Factored models. [Also presenting at another symposium.]
• Valentina Bayer (Oregon St.). Primary interests: approximations and heuristics.
• Chip White (Michigan). Primary interests: mathematical and algorithmic foundations, approximations and heuristics. Presenting: something original.
• Nicholas Roy (CMU). Primary interests: robotics. Presenting: Robot planning under uncertainty.
• Jay Chawla (Maryland). Primary interests: mathematical and algorithmic foundations. Presenting: something by Steve Marcus?
• Keith Doty, Drew Bagnell (Mekatronix, UFL). Primary interests: robotics. Presenting: robot demo.
• Pier Luca Lanzi (Politecnico di Milano). Primary interests: reinforcement learning. Presenting: classifiers.
• Claude Touzet (CESAR-ORNL). Primary interests: robot. Presenting: cooperative robot learning. Statement of interest.
• Trevor Darrell (Interval). Primary interests: other applications (vision). Presenting: Active vision problem.
• Larry Pyeatt (Colorado St.). Primary interests: reinforcement learning. Presenting: learning sequences.
• Loren Platzman (self). Primary interest: approximations and heuristics. Presenting: finite-memory approaches.
• Judy Goldsmith, Chris Lusena, Tong Li, Chris Wells, Shelia Sittinger (U. Kentucky). Primary interests: mathematical and algorithmic foundations. Presenting: complexity results and such.
• Niels Peek (Utrecht). Primary interests: factored models. Presenting: something relevant.
• Milos Hauskrecht. Primary interests: approximations and heuristics, other applications. Presenting: approximations, medical application
• Omid Madani (Washington). Primary interests: mathematical and algorithmic foundations. Presenting: Complexity and computability analyses.
• Sascha E. Engelbrecht (Umass). Presenting: Planning with Delayed State Information (official).
• Hector Geffner, Blai Bonet (Simon Bolivar). Presenting: POMDPs for planning. Overview of factored methods.
• Steve Majercik (Duke). Presenting: Searching for small plans in POMDPs.
• Eric Hansen (Mississippi St.). Presenting: Finite-state controllers for POMDPs.
• Rich Washington (NASA). Presenting: POMDP application or algorithm.

Presentations by Focus Area

Introduction

Mathematical and Algorithmic Foundations

Approximations and Heuristics

Factored Models

Reinforcement Learning

Robotic Applications

Other Applications

Extensions and Specializations

Michael L. Littman, Ph.D.

Assistant Professor

Department of Computer Science

Duke University, Durham, NC 27708-0129

Office: D209 LSRC

Phone: 919-660-6537

Fax: 919-660-6519

mlittman@cs.duke.edu