History-Based Controller Design and Optimization for Partially Observable MDPs
Partially observable MDPs provide an elegant framework forsequential decision making. Finite-state controllers (FSCs) are often used to represent policies for infinite-horizon problems as they offer a compact representation, simple-to-execute plans, and adjustable tradeoff between computational comp...
Saved in:
Main Authors: | KUMAR, Akshat, ZILBERSTEIN, Shlomo |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2015
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/2915 https://ink.library.smu.edu.sg/context/sis_research/article/3915/viewcontent/History_Based_Controller_Design_afv.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Dynamic Programming Approximations for Partially Observable Stochastic Games
by: KUMAR, Akshat, et al.
Published: (2009) -
Event-Detecting Multi-Agent MDPs: Complexity and Constant-Factor Approximation
by: KUMAR, Akshat, et al.
Published: (2009) -
Message-Passing Algorithms for Quadratic Programming Formulations of MAP Estimation
by: KUMAR, Akshat, et al.
Published: (2011) -
Message-Passing Algorithms for Large Structured Decentralized POMDPs
by: KUMAR, Akshat, et al.
Published: (2011) -
MAP Estimation for Graphical Models by Likelihood Maximization
by: KUMAR, Akshat, et al.
Published: (2010)