Sampling-based algorithms for continuous-time POMDPs
Name
Karaman_Sampling-based algorithms.pdf
Size
1.48 MB
Format
Adobe PDF
Checksum (MD5)
63cfc23cec33ba43fdaf4e61eec9b1a3
Author(s)
Chaudhari, Pratik Anil
Karaman, Sertac
Hsu, David
Frazzoli, Emilio
Date Issued
June 2013
Journal
Proceedings of the 2013 American Control Conference (ACC)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Chaudhari, Pratik Anil et al. "Sampling-based algorithms for continuous-time POMDPs." IEEE American Control Conference (ACC), 2013.
Version
Author's final manuscript
Abstract
This paper focuses on a continuous-time, continuous-space formulation of the stochastic optimal control problem with nonlinear dynamics and observation noise. We lay the mathematical foundations to construct, via incremental sampling, an approximating sequence of discrete-time finite-state partially observable Markov decision processes (POMDPs), such that the behavior of successive approximations converges to the behavior of the original continuous system in an appropriate sense. We also show that the optimal cost function and control policies for these POMDP approximations converge almost surely to their counterparts for the underlying continuous system in the limit. We demonstrate this approach on two popular continuous-time problems, viz., the Linear-Quadratic-Gaussian (LQG) control problem and the light-dark domain problem.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6580549
