Sciweavers

467 search results - page 69 / 94
» Learning of Agents with Limited Resources
Sort
View
ALT
2009
Springer
14 years 4 months ago
Pure Exploration in Multi-armed Bandits Problems
Abstract. We consider the framework of stochastic multi-armed bandit problems and study the possibilities and limitations of strategies that explore sequentially the arms. The stra...
Sébastien Bubeck, Rémi Munos, Gilles...
ATAL
2006
Springer
13 years 11 months ago
Adaptive Pricing for Customers with Probabilistic Valuations
Abstract. In this paper, we examine the problem of choosing discriminatory prices for customers with probabilistic valuations and a seller with indistinguishable copies of a good. ...
Michael Benisch, James Andrews, Norman M. Sadeh
AAAI
2007
13 years 10 months ago
Comprehending and Generating Apt Metaphors: A Web-driven, Case-based Approach to Figurative Language
Examples of figurative language can range from the explicit and the obvious to the implicit and downright enigmatic. Some simpler forms, like simile, often wear their meanings on...
Tony Veale, Yanfen Hao
ATAL
2008
Springer
13 years 10 months ago
Undominated VCG redistribution mechanisms
Many important problems in multiagent systems can be seen as resource allocation problems. For such problems, the well-known Vickrey-Clarke-Groves (VCG) mechanism is efficient, in...
Mingyu Guo, Vincent Conitzer
AGENTS
1997
Springer
14 years 1 days ago
Adaptable Local Level Arbitration of Behaviors
During the last few years, and in an attempt to provide an ecient alternative to classical methods to designing robot control structures, the behavior-based approach has emerged....
Mohamed Salah Hamdi, Karl Kaiser