Ruth Bergman, Ronald L. Rivest  Home/Search
Context
Related
| mit.edu/~rivest/Be...rtFromASequence.ps mit.edu/%7Erivest/...rtFromASequence.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: mit.edu/~rivest/publications (more) From: mit.edu/~rivest/publications (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We examine the problem of finding a good expert from a sequence of experts. Each expert has an "error rate"; we wish to find an expert with a low error rate. However, each expert's error rate is unknown and can only be estimated by a sequence of experimental trials. Moreover, the distribution of error rates is also unknown. Given a bound on the total number of trials, there is thus a tradeoff between the number of experts examined and the accuracy of estimating their error rates. We present a... (Update)
Similar documents (at the sentence level):
78.1%: Picking the Best Expert from a Sequence - Bergman, Rivest (Correct)
65.6%: Learning Models of Environments with Manifest Causal Structure - Bergman (1995) (Correct)
Active bibliography (related documents): More All
0.1: Complexity Analysis of Real-Time Reinforcement Learning.. - Koenig, Simmons (1997) (Correct)
0.1: A Mathematical Analysis Of Actor-Critic Architectures For.. - Williams (1990) (Correct)
0.1: Connectionist Environment Modelling In A Real Robot - Chesters, Hayes (1994) (Correct)
Similar documents based on text: More All
0.2: Expert Finding Systems for Organizations: Problem and Domain .. - Yimam-Seid, KOBSA (2002) (Correct)
0.0: A study of the Bergman projection in certain Hartogs domains - Kiselman (1991) (Correct)
0.0: Bergman Isometries Between Convex Domains In C² Which Are.. - Pagano (1997) (Correct)
BibTeX entry: (Update)
@misc{ bergman-picking,
author = "Ruth Bergman and Ronald L. Rivest",
title = "Picking the Best Expert from a Sequence",
url = "citeseer.ist.psu.edu/bergman95picking.html" }
Citations (may not include all citations):658 Learning from Delayed Rewards (context) - Watkins - 1989
300 SOAR: An Architecture for General Intelligence (context) - Laird, Newell et al. - 1978 ACM DBLP
126 Learning in Embedded Systems (context) - Kaelbling - 1990 ACM
81 Sequential Analysis (context) - Wald - 1947
80 Mathematical Statistics and Data Analysis (context) - Rice - 1988
67 Reinforcement Learning Architectures for Animats (context) - Sutton - 1991 ACM
52 Made-Up Minds: A Constructivist Approach to Artificial Intel.. (context) - Drescher - 1989 DBLP
40 Properties of the bucket brigade algorithm (context) - Holland - 1985
7 First Results with DYNA (context) - Sutton - 1990
Documents on the same site (http://theory.lcs.mit.edu/~rivest/publications.html): More
Game Tree Searching by Min/Max Approximation - Rivest (1995) (Correct)
Complete Variable-Length "Fix-Free" Codes - Gillman, Rivest (1995) (Correct)
Geometric Cryptography: Identification by Angle Trisection - Burmester, Rivest, Shamir (1997) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC