RAO*: an Algorithm for Chance-Constrained POMDP’s
Name
2016_AAAI_rao.pdf
Size
330.34 KB
Format
Adobe PDF
Checksum (MD5)
72bf9c3886b5e322b79e9ef883e51184
Author(s)
Santana, Pedro
Thiebaux, Sylvie
Williams, Brian Charles
Date Issued
February 2016
Journal
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16)
Publisher
Association for the Advancement of Artificial Intelligence
Citation
Santana, Pedro, Sylvie Thiebaux, and Brian Williams. "RAO*: an Algorithm for Chance-Constrained POMDP’s." Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (February 2016).
Version
Author's final manuscript
Abstract
Autonomous agents operating in partially observable stochastic environments often face the problem of optimizing expected performance while bounding the risk of violating safety constraints. Such problems can be modeled as chance-constrained POMDP’s (CC-POMDP’s). Our first contribution is a systematic derivation of execution risk in POMDP domains, which improves upon how chance constraints are handled in the constrained POMDP literature. Second, we present RAO*, a heuristic forward search algorithm producing optimal, deterministic, finite-horizon policies for CC-POMDP’s. In addition to the utility heuristic, RAO* leverages an admissible execution risk heuristic to quickly detect and prune overly-risky policy branches. Third, we demonstrate the usefulness of RAO* in two challenging domains of practical interest: power supply restoration and autonomous science agents
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://www.aaai.org/Conferences/AAAI/2016/aaai16accepted-papers.pdf
