F. Menczer, Life-like agents: Internalizing local cues for reinforcement learning and evolution, PhD thesis, University of California, San Diego Department of Computer Sciences and Engineering, 1998. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Complementing Search Engines with Online Web Mining Agents - Menczer (2002) (2 citations) Self-citation (Menczer) (Correct)
No context found.
F. Menczer, Life-like agents: Internalizing local cues for reinforcement learning and evolution, PhD thesis, University of California, San Diego Department of Computer Sciences and Engineering, 1998.
Efficient and Scalable Pareto Optimization by.. - Menczer, Degeratu.. (2000) (2 citations) Self-citation (Menczer) (Correct)
.... technology (Menczer and Monge, 1999; Menczer and Belew, 2000) In previous work, we tested the feasibility of local selection algorithms for distributed information retrieval problems by building artificial graphs to model different aspects of Web like search environments (Menczer and Belew, 1998; Menczer, 1998). Here we outline the results of a related experiment, engineered to model a multi objective environment. 3.1.1 Problem description The problem can be broadly described as searching large graphs in sublinear time. Imagine a very large graph, where each node is associated with a Boolean payoff. ....
....that we might attack with ELSA include distributed scheduling, distributed resource allocation, and constrained search. Local selection has already been applied to agent based distributed information retrieval, e.g. for autonomous on line Web browsing. The InfoSpiders project (Menczer, 1997; Menczer, 1998; Menczer and Belew, 2000) shows promise in taking advantage of several properties of evolutionary local selection algorithms: i) coverage, for quickly locating many relevant documents; ii) distributed nature, to conserve bandwidth by enabling agents to run on the remote servers where documents ....
[Article contains additional citation context not shown here]
Menczer, F. (1998). Life-like agents: Internalizing local cues for reinforcement learning and evolution. PhD thesis, University of California, San Diego.
Evolving Heterogeneous Neural Agents by Local Selection - Menczer, Street, Degeratu (2000) (1 citation) Self-citation (Menczer) (Correct)
.... We tested the feasibility of local selection algorithms for distributed information retrieval problems by building artificial graphs to model different MIT Press Math6X9 1999 09 30:19:43 Page 12 Evolving Heterogeneous Neural Agents by Local Selection 13 aspects of Web like search environments [42, 38]. In each experiment we constructed a large graph, where each node was associated with some payoff. Nodes, edges, and payoffs modeled hypertext documents, hyperlinks, and relevance, respectively. The population of agents visited the graph as agents traversed its edges. The idea was to maximize ....
....results [45, 43] For example, figure 1.7 shows the result of a comparison in performance between InfoSpiders and best first search, on a hypertext collec MIT Press Math6X9 1999 09 30:19:43 Page 15 16 Filippo Menczer, W. Nick Street, and Melania Degeratu tion from Encyclopaedia Britannica Online [38]. InfoSpiders had a significant advantage when the relevant set was not too many links away from the starting page. These results point to the need for hybrid systems that use search engines to provide good starting points and InfoSpiders to search for recent information. 80 84 88 92 96 100 ....
[Article contains additional citation context not shown here]
F Menczer. Life-like agents: Internalizing local cues for reinforcement learning and evolution. PhD thesis, University of California, San Diego, 1998.
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