Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.


Sufficient statistics for multiple agents

We describe a notion of sufficient statistics for decision, estimation or control problems involving multiple players. As in the classical single-player setting, sufficient statistics contain all of the information necessary for the players to make optimal decisions. In the multi-agent setting, we construct such sufficient statistics via a convex relaxation of the feasible set of the corresponding decision problem. We show that these statistics may be updated recursively, and may be constructed by appropriately composing the corresponding single-player statistics. We present algorithms for this construction when the information pattern is defined by an appropriate graph.

Type of Seminar:
Control Seminar Series
Prof. Sanjay Lall
Stanford University
Nov 04, 2015   17:15

Contact Person:

Prof. Florian Dörfler
File Download:

Request a copy of this publication.
Biographical Sketch:
Sanjay Lall is Professor of Electrical Engineering at Stanford University. Previously he was a Research Fellow at the California Institute of Technology in the Department of Control and Dynamical Systems, and prior to that he was NATO Research Fellow at Massachusetts Institute of Technology, in the Laboratory for Information and Decision Systems. He was also a visiting scholar at Lund Institute of Technology in the Department of Automatic Control. He received the Ph.D. in Engineering and B.A. in Mathematics from the University of Cambridge, England. Professor Lall's research focuses on the development of advanced engineering methodologies for the design of control systems, and his work addresses problems including decentralized control and model reduction. Professor Lall received the O. Hugo Schuck Best Paper Award at the American Control Conference in 2013, the George S. Axelby Outstanding Paper Award by the IEEE Control Systems Society in 2007, the NSF Career award in 2007, Presidential Early Career Award for Scientists and Engineers (PECASE) in 2007, and the Graduate Service Recognition Award from Stanford University in 2005. With his students, he received the best student paper award at the IEEE Conference on Decision and Control in 2005 and the best student paper award at the IEEE International Conference on Power Systems Technology (POWERCON) in 2012.