Dual formulations for optimizing Dec-POMDP controllers
Decentralized POMDP is an expressive model for multi-agent planning. Finite-state controllers (FSCs)---often used to represent policies for infinite-horizon problems---offer a compact, simple-to-execute policy representation. We exploit novel connections between optimizing decentralized FSCs and the...
Saved in:
Main Authors: | Akshat KUMAR, MOSTAFA, Hala, ZILBERSTEIN, Shlomo |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2016
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/3395 https://ink.library.smu.edu.sg/context/sis_research/article/4396/viewcontent/DualFormulations.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Prioritized Shaping of Models for Solving DEC-POMDPs
by: VARAKANTHAM, Pradeep Reddy, et al.
Published: (2012) -
Message-Passing Algorithms for Large Structured Decentralized POMDPs
by: KUMAR, Akshat, et al.
Published: (2011) -
Anytime Planning for Decentralized POMDPs using Expectation Maximization
by: KUMAR, Akshat, et al.
Published: (2010) -
Constraint-Based Dynamic Programming for Decentralized POMDPs with Structured Interactions
by: KUMAR, Akshat, et al.
Published: (2009) -
Shortest path based decision making using probabilistic inference
by: Akshat KUMAR,
Published: (2016)