Speeding up top-down attention control learning by using full observation knowledge

  • Authors:

  • N. Noori;M. Nili Ahmadabadi;M. S. Mirian;B. N. Araabi

  • Affiliations:

  • Robotics and AI Lab, Control and Intelligent Processing Center of Excellence, Department of Electrical and ComputerEngineering, University of Tehran, Tehran, Iran;Robotics and AI Lab, Control and Intelligent Processing Center of Excellence, Department of Electrical and ComputerEngineering, University of Tehran, Tehran, Iran;Robotics and AI Lab, Control and Intelligent Processing Center of Excellence, Department of Electrical and ComputerEngineering, University of Tehran, Tehran, Iran;Robotics and AI Lab, Control and Intelligent Processing Center of Excellence, Department of Electrical and ComputerEngineering, University of Tehran, Tehran, Iran

  • Venue:
  • CIRA'09 Proceedings of the 8th IEEE international conference on Computational intelligence in robotics and automation
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

we present a general mathematical description of the top-down attention control problem. Three important components are identified in the model: context extraction, attention focus and decision making. The context gives a coarse blurry representation of the whole input; the attention module models the focus of attention on a limited part of input, and the decision making component accounts the final decision of the agent for its motory actions. In order to achieve a faster convergence of attention learning in the online phase, an omine optimization step is performed in advance. To do so, we incorporate the knowledge of a full observer agent that bas approximately learned the optimal decision making of the task. The simulation results show that by employing our algorithm, the learning speed is improved.