Investigations of continual computation

Dafna Shahaf*, Eric Horvitz

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations


Autonomous agents that sense, reason, and act in real-world environments for extended periods often need to solve streams of incoming problems. Traditionally, effort is applied only to problems that have already arrived and have been noted. We examine continual computation methods that allow agents to ideally allocate time to solving current as well as potential future problems under uncertainty. We first review prior work on continual computation. Then, we present new directions and results, including the consideration of shared subtasks and multiple tasks. We present results on the computational complexity of the continual-computation problem and provide approximations for arbitrary models of computational performance. Finally, we review special formulations for addressing uncertainty about the best algorithm to apply, learning about performance, and considering costs associated with delayed use of results.

Original languageAmerican English
Title of host publicationIJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence
PublisherInternational Joint Conferences on Artificial Intelligence
Number of pages7
ISBN (Print)9781577354260
StatePublished - 2009
Externally publishedYes
Event21st International Joint Conference on Artificial Intelligence, IJCAI 2009 - Pasadena, United States
Duration: 11 Jul 200916 Jul 2009

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823


Conference21st International Joint Conference on Artificial Intelligence, IJCAI 2009
Country/TerritoryUnited States


Dive into the research topics of 'Investigations of continual computation'. Together they form a unique fingerprint.

Cite this