Sciweavers

4255 search results - page 418 / 851
» On Learning Boolean Functions
Sort
View
ICML
1990
IEEE
15 years 10 months ago
Explanations of Empirically Derived Reactive Plans
Given an adequate simulation model of the task environment and payoff function that measures the quality of partially successful plans, competition-based heuristics such as geneti...
Diana F. Gordon, John J. Grefenstette
IADIS
2004
15 years 8 months ago
Collaborative Task and Communication Protocol Among Pedagogical Agents in Teaching Task
In recent years, there are many educational systems which incorporate the agents such as pedagogical agents and peer agents, as a means to realize the teaching, coaching and suppo...
Ryo Takaoka, Toshio Okamoto
NN
2006
Springer
120views Neural Networks» more  NN 2006»
15 years 6 months ago
Computational intelligence in earth sciences and environmental applications: Issues and challenges
This paper introduces a generic theoretical framework for predictive learning, and relates it to data-driven and learning applications in earth and environmental sciences. The iss...
Vladimir Cherkassky, Vladimir M. Krasnopolsky, Dim...
TFS
2008
94views more  TFS 2008»
15 years 6 months ago
Hierarchical Fuzzy CMAC for Nonlinear Systems Modeling
Abstract--Since the fuzzy cerebellar model articulation controller (FCMAC) uses linguistic variables, it is highly intuitive and easily comprehended. Despite the FCMAC's good ...
Wen Yu, Floriberto Ortiz Rodriguez, Marco A. Moren...
ICMLA
2010
15 years 4 months ago
Multimodal Parameter-exploring Policy Gradients
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
Frank Sehnke, Alex Graves, Christian Osendorfer, J...