JSM 2003 Online Program

Abstract #300548

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page

Activity Number:	108
Type:	Invited
Date/Time:	Monday, August 4, 2003 : 10:30 AM to 12:20 PM
Sponsor:	IMS
Abstract - #300548
Title:	Value Function Approximation in Dynamic Programming: History and Recent Developments
Author(s):	Benjamin Van Roy*+
Companies:	Stanford University
Address:	Terman 427, Mgt. Science & Engineering, Stanford, CA, 94305-4023,
Keywords:	multistage decisions ; reinforcement learning
Abstract:	Dynamic programming value function approximation has been a subject of discussion in the operations research literature since the 1950s. However, progress in this area has accelerated significantly over the past two decades, fueled to a large extent by activity in artificial intelligence. We will review work on value function approximation, including recent developments involving a linear programming formulation. The talk will touch on applications in backgammon, queueing, and Tetris.

The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program