Sciweavers

123 search results - page 9 / 25
» Learning Non-Explicit Control Parameters of Self-Organizing ...
Sort
View
ESAW
2008
Springer
13 years 9 months ago
Contribution to the Control of a MAS's Global Behaviour: Reinforcement Learning Tools
Reactive multi-agent systems present global behaviours uneasily linked to their local dynamics. When it comes to controlling such a system, usual analytical tools are difficult to ...
François Klein, Christine Bourjot, Vincent ...
ICML
2004
IEEE
14 years 8 months ago
Learning and discovery of predictive state representations in dynamical systems with reset
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
Michael R. James, Satinder P. Singh
TFS
2008
157views more  TFS 2008»
13 years 7 months ago
Efficient Self-Evolving Evolutionary Learning for Neurofuzzy Inference Systems
Abstract--This study proposes an efficient self-evolving evolutionary learning algorithm (SEELA) for neurofuzzy inference systems (NFISs). The major feature of the proposed SEELA i...
Cheng-Jian Lin, Cheng-Hung Chen, Chin-Teng Lin
CCIA
2005
Springer
14 years 1 months ago
Direct Policy Search Reinforcement Learning for Robot Control
— This paper proposes a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, whe...
Andres El-Fakdi, Marc Carreras, Narcís Palo...
ICRA
2000
IEEE
236views Robotics» more  ICRA 2000»
13 years 12 months ago
A General Learning Approach to Multisensor Based Control using Statistic Indices
We propose a concept for integrating multiple sensors in real-time robot control. To increase the controller robustness under diverse uncertainties, the robot systematically gener...
Yorck von Collani, Markus Ferch, Jianwei Zhang, Al...