Sciweavers

2103 search results - page 170 / 421
» Approximate Learning of Dynamic Models
Sort
View
ATAL
2010
Springer
15 years 6 months ago
Frequency adjusted multi-agent Q-learning
Multi-agent learning is a crucial method to control or find solutions for systems, in which more than one entity needs to be adaptive. In today's interconnected world, such s...
Michael Kaisers, Karl Tuyls
SASO
2008
IEEE
15 years 11 months ago
Self-Organization of Creole Community in Spatial Language Dynamics
Creolization is a self-organization process of new language community. Thus far, a simulation study of the emergence of creoles has been reported in the mathematical framework. In...
Makoto Nakamura, Takashi Hashimoto, Satoshi Tojo
IDEAL
2000
Springer
15 years 8 months ago
Learning of Virtual Dealers in an Artificial Market: Comparison with Interview Data
Abstract. In this study we used a new agent-based approach, an artificial market approach, to analyze the ways that dealers process the information in financial news. We compared b...
Kiyoshi Izumi, Kazuhiro Ueda
COLT
2003
Springer
15 years 10 months ago
Lower Bounds on the Sample Complexity of Exploration in the Multi-armed Bandit Problem
We consider the Multi-armed bandit problem under the PAC (“probably approximately correct”) model. It was shown by Even-Dar et al. [5] that given n arms, it suffices to play th...
Shie Mannor, John N. Tsitsiklis
HCI
2009
15 years 2 months ago
Adaptive Learning via Social Cognitive Theory and Digital Cultural Ecosystems
This paper will look at the human predisposition to oral tradition and its effectiveness as a learning tool to convey mission-critical information. After exploring the effectivenes...
Joseph Juhnke, Adam R. Kallish