Sciweavers

150 search results - page 9 / 30
» Managing Dynamic Multi-Agent Simple Temporal Network
Sort
View
102
Voted
ML
1998
ACM
136views Machine Learning» more  ML 1998»
15 years 2 days ago
Co-Evolution in the Successful Learning of Backgammon Strategy
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
Jordan B. Pollack, Alan D. Blair
WWW
2008
ACM
16 years 1 months ago
Facetnet: a framework for analyzing communities and their evolutions in dynamic networks
We discover communities from social network data, and analyze the community evolution. These communities are inherent characteristics of human interaction in online social network...
Yu-Ru Lin, Yun Chi, Shenghuo Zhu, Hari Sundaram, B...
NIPS
1996
15 years 1 months ago
Why did TD-Gammon Work?
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference learning for other applications or ...
Jordan B. Pollack, Alan D. Blair
CASCON
1996
113views Education» more  CASCON 1996»
15 years 1 months ago
Network management views using delegated agents
The lack of an appropriate external data model is one of the reasons for the dearth of eective network management applications. Many network management computations over Managemen...
Germán S. Goldszmidt
107
Voted
POLICY
2009
Springer
15 years 7 months ago
The Zodiac Policy Subsystem: A Policy-Based Management System for a High-Security MANET
Abstract—Zodiac (Zero Outage Dynamic Intrinsically Assurable Communities) is an implementation of a high-security MANET, resistant to multiple types of attacks, including Byzanti...
Yuu-Heng Cheng, Mariana Raykova, Alexander Poylish...