On the structure of decentralized controllers in networked MDPs
- Creators
- Horowitz, Matanya
Abstract
This work considers the problem of constructing optimal decentralized controllers for networked Markov Decision Processes (MDPs). A number of subsystems, each modeled as an MDP, are dynamically coupled through a network and affect one another with delay. Each subsystem has a corresponding controller which has perfect knowledge of the local state and may communicate its state to the other controllers over a noise-free channel with fixed delay. The problem is framed in terms of a coordinator with access to the shared information of the controllers, leading to a dynamic programming problem to calculate optimal policies. Further, under the criteria of partial nestedness the dynamic program exhibits additional factored structure, leading to more efficient synthesis of the optimal policy.
Additional Information
© 2013 IEEE. Matanya Horowitz is supported by a NSF Graduate Research Fellowship. This research was in part supported by NSF NetSE, AFOSR, the Institute for Collaborative Biotechnologies through grant W911NF-09-0001 from the U.S. Army Research Office, and from MURIs "Scalable, Data-Driven, and Provably-Correct Analysis of Networks" (ONR) and "Tools for the Analysis and Design of Complex Multi-Scale Networks" (ARO). The content does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferredAdditional details
- Eprint ID
- 73743
- DOI
- 10.1109/CDC.2013.6760815
- Resolver ID
- CaltechAUTHORS:20170125-164005961
- NSF Graduate Research Fellowship
- Air Force Office of Scientific Research (AFOSR)
- W911NF-09-0001
- Army Research Office (ARO)
- Office of Naval Research (ONR)
- Created
-
2017-01-26Created from EPrint's datestamp field
- Updated
-
2021-11-11Created from EPrint's last_modified field