Efficiently gathering information in costly domains

This paper proposes a novel technique for allocating information gathering actions in settings where agents need to choose among several alternatives, each of which provides a stochastic outcome to the agent. Samples of these outcomes are available to agents prior to making decisions and obtaining further samples is associated with a cost. The paper formalizes the task of choosing the optimal sequence of information gathering actions in such settings and establishes it to be NP-Hard. It suggests a novel estimation technique for the optimal number of samples to obtain for each of the alternatives. The approach takes into account the trade-offs associated with using prior samples to choose the best alternative and paying to obtain additional samples. This technique is evaluated empirically in several different settings using real data. Results show that our approach was able to significantly outperform alternative algorithms from the literature for allocating information gathering actions in similar types of settings. These results demonstrate the efficacy of our approach as an efficient, tractable technique for deciding how to acquire information when agents make decisions under uncertain conditions.

[1]  Solomon Eyal Shimony,et al.  Observation Subset Selection as Local Compilation of Performance Profiles , 2008, UAI.

[2]  Shlomo Zilberstein,et al.  A Value-Driven System for Autonomous Information Gathering , 2004, Journal of Intelligent Information Systems.

[3]  Stephen F. Smith,et al.  The Max K-Armed Bandit: A New Model of Exploration Applied to Search Heuristic Selection , 2005, AAAI.

[4]  Eric Horvitz,et al.  An approximate nonmyopic computation for value of information , 1994, UAI 1994.

[5]  Vincent Conitzer,et al.  Definition and Complexity of Some Basic Metareasoning Problems , 2003, IJCAI.

[6]  Sarit Kraus,et al.  A statistical decision-making model for choosing among multiple alternatives , 2007, AAMAS '07.

[7]  Rina Azoulay-Schwartz,et al.  Acquiring an Optimal Amount of Information for Choosing from Alternatives , 2002, CIA.

[8]  C. H. Edwards,et al.  Calculus and Analytic Geometry , 1982 .

[9]  Russell Greiner,et al.  Active Model Selection , 2004, UAI.

[10]  Andreas Krause,et al.  Optimal Nonmyopic Value of Information in Graphical Models - Efficient Algorithms and Theoretical Limits , 2005, IJCAI.

[11]  Jürgen Branke,et al.  Sequential Sampling to Myopically Maximize the Expected Value of Information , 2010, INFORMS J. Comput..

[12]  Lise Getoor,et al.  VOILA: Efficient Feature-value Acquisition for Classification , 2007, AAAI.

[13]  Russell G. Almond,et al.  On Test Selection Strategies for Belief Networks , 1995, AISTATS.

[14]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[15]  Sarit Kraus,et al.  Choosing between heuristics and strategies: an enhanced model for decision-making , 2005, IJCAI.

[16]  Stephen F. Smith,et al.  An Asymptotically Optimal Algorithm for the Max k-Armed Bandit Problem , 2006, AAAI.

[17]  Andreas Krause,et al.  Optimal Value of Information in Graphical Models , 2009, J. Artif. Intell. Res..

[18]  Andreas Krause,et al.  Near-optimal Observation Selection using Submodular Functions , 2007, AAAI.

[19]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[20]  Piotr J. Gmytrasiewicz,et al.  Time sensitive sequential myopic information gathering , 1999, Proceedings of the 32nd Annual Hawaii International Conference on Systems Sciences. 1999. HICSS-32. Abstracts and CD-ROM of Full Papers.

[21]  P. W. Jones,et al.  Bandit Problems, Sequential Allocation of Experiments , 1987 .