Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions

Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions.
Peter Stone, Robert E. Schapire, Michael L. Littman, János A. Csirik, and David McAllester.
Journal of Artificial Intelligence Research, 19:209–242, 2003.
Available from journal's web page.

Download

[PDF] [postscript] 

Abstract

Auctions are becoming an increasingly popular method for transacting business, especially over the Internet. This article presents a general approach to building autonomous bidding agents to bid in multiple simultaneous auctions for interacting goods. A core component of our approach learns a model of the empirical price dynamics based on past data and uses the model to analytically calculate, to the greatest extent possible, optimal bids. We introduce a new and general boosting-based algorithm for conditional density estimation problems of this kind, i.e., supervised learning problems in which the goal is to estimate the entire conditional distribution of the real-valued label. This approach is fully implemented as ATTac, a top-scoring agent in the second Trading Agent Competition (TAC-01). We present experiments demonstrating the effectiveness of our boosting-based price predictor relative to several reasonable alternatives.

BibTeX Entry

@article(JAIR-tac01,
    Author={Peter Stone and Robert E.~Schapire and Michael L.~Littman and J\'{a}nos A.~Csirik and David McAllester},
    Title="Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions",
    Journal="Journal of Artificial Intelligence Research",
    Year="2003",volume="19",pages="209--242",
    abstract={
              Auctions are becoming an increasingly popular method for
              transacting business, especially over the Internet.
              This article presents a general approach to building
              autonomous bidding agents to bid in multiple
              simultaneous auctions for interacting goods.  A core
              component of our approach learns a model of the
              empirical price dynamics based on past data and uses the
              model to analytically calculate, to the greatest extent
              possible, optimal bids.  We introduce a new and general
              boosting-based algorithm for conditional density
              estimation problems of this kind, i.e., supervised
              learning problems in which the goal is to estimate the
              entire conditional distribution of the real-valued
              label.  This approach is fully implemented as ATTac, a
              top-scoring agent in the second Trading Agent
              Competition (TAC-01).  We present experiments
              demonstrating the effectiveness of our boosting-based
              price predictor relative to several reasonable
              alternatives.
    },
    wwwnote = {Available from <a href="http://www.jair.org/papers/paper1200.html">journal's web page</a>.},
)

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 17, 2021 22:18:58