Selecting computations: Theory and applications

Nicholas Hay, Stuart Russell, David Tolpin, Solomon Eyal Shimony

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

Abstract

Sequential decision problems are often approximately solvable by simulating possible future action sequences. Metalevel decision procedures have been developed for selecting which action sequences to simulate, based on estimating the expected improvement in decision quality that would result from any particular simulation; an example is the recent work on using bandit algorithms to control Monte Carlo tree search in the game of Go. In this paper we develop a theoretical basis for metalevel decisions in the statistical framework of Bayesian selection problems, arguing (as others have done) that this is more appropriate than the bandit framework. We derive a number of basic results applicable to Monte Carlo selection problems, including the first finite sampling bounds for optimal policies in certain cases; we also provide a simple counterexample to the intuitive conjecture that an optimal policy will necessarily reach a decision in all cases. We then derive heuristic approximations in both Bayesian and distribution-free settings and demonstrate their superiority to bandit-based heuristics in one-shot decision problems and in Go.

Original languageAmerican English
Title of host publicationUncertainty in Artificial Intelligence - Proceedings of the 28th Conference, UAI 2012
Pages346-355
Number of pages10
StatePublished - 1 Dec 2012
Event28th Conference on Uncertainty in Artificial Intelligence, UAI 2012 - Catalina Island, CA, United States
Duration: 15 Aug 201217 Aug 2012

Publication series

NameUncertainty in Artificial Intelligence - Proceedings of the 28th Conference, UAI 2012

Conference

Conference28th Conference on Uncertainty in Artificial Intelligence, UAI 2012
Country/TerritoryUnited States
CityCatalina Island, CA
Period15/08/1217/08/12

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Selecting computations: Theory and applications'. Together they form a unique fingerprint.

Cite this