Page 1 |
Save page Remove page | Previous | 1 of 146 | Next |
|
small (250x250 max)
medium (500x500 max)
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
Subset |
TOWARDS EFFICIENT PLANNING FOR REAL WORLD PARTIALLY
OBSERVABLE DOMAINS
by
Pradeep Varakantham
A Dissertation Presented to the
FACULTY OF THE GRADUATE SCHOOL
UNIVERSITY OF SOUTHERN CALIFORNIA
In Partial Fulfillment of the
Requirements for the Degree
DOCTOR OF PHILOSOPHY
(COMPUTER SCIENCE)
May 2007
Copyright 2007 Pradeep Varakantham
Object Description
| Title | Towards efficient planning for real world partially observable domains |
| Author | Varakantham, Pradeep |
| Author email | varakant@usc.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2007-02-06 |
| Date submitted | 2007 |
| Restricted until | Unrestricted |
| Date published | 2007-03-30 |
| Advisor (committee chair) | Tambe, Milind |
| Advisor (committee member) |
Marsella, Stacy Ordonez, Fernando Koenig, Sven Veloso, Manuela |
| Abstract | My research goal is to build large-scale intelligent systems (both single- and multi-agent) that reason with uncertainty in complex, real-world environments. I foresee an integration of such systems in many critical facets of human life ranging from intelligent assistants in hospitals to offices, from rescue agents in large scale disaster response to sensor agents tracking weather phenomena in earth observing sensor webs, and others. In my thesis, I have taken steps towards achieving this goal in the context of systems that operate in partially observable domains that also have transitional (non-deterministic outcomes to actions) uncertainty. Given this uncertainty, Partially Observable Markov Decision Problems (POMDPs) and Distributed POMDPs present themselves as natural choices for modeling these domains.; Unfortunately, the significant computational complexity involved in solving POMDPs (PSPACE-Complete) and Distributed POMDPs (NEXP-Complete) is a key obstacle. Due to this significant computational complexity, existing approaches that provide exact solutions do not scale, while approximate solutions do not provide any usable guarantees on quality. My thesis addresses these issues using the following key ideas: The first is exploiting structure in the domain. Utilizing the structure present in the dynamics of the domain or the interactions between the agents allows improved efficiency without sacrificing on the quality of the solution. The second is direct approximation in the value space. This allows for calculated approximations at each step of the algorithm, which in turn allows us to provide usable quality guarantees; such quality guarantees may be specified in advance. In contrast, the existing approaches approximate in the belief space leading to an approximation in the value space (indirect approximation in value space), thus making it difficult to compute functional bounds on approximations. In fact, these key ideas allow for the efficient computation of optimal and quality bounded solutions to complex, large-scale problems, that were not in the purview of existing algorithms. |
| Keyword | decision making under uncertainty |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Type | texts |
| Legacy record ID | usctheses-m339 |
| Rights | Varakantham, Pradeep |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | http://www.usc.edu/isd/libraries/services/ask_a_librarian/email/ |
| Filename | etd-Varakantham-20070330 |
| Archival file | uscthesesreloadpub_Volume26/etd-Varakantham-20070330.pdf |
Description
| Title | Page 1 |
| Full text | TOWARDS EFFICIENT PLANNING FOR REAL WORLD PARTIALLY OBSERVABLE DOMAINS by Pradeep Varakantham A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (COMPUTER SCIENCE) May 2007 Copyright 2007 Pradeep Varakantham |
Comments
Post a Comment for Page 1
