Advanced

Attention control learning in the decision space using state estimation

Gharaee, Zahra LU ; Fatehi, Alireza; Mirian, Maryam and Nili Ahmadabadi, Majid (2014) In International Journal of Systems Science 47(7). p.1659-1674
Abstract
The main goal of this paper is modelling attention while using it in efficient path planning of mobile robots. The key challenge in concurrently aiming these two goals is how to make an optimal, or near-optimal, decision in spite of time and processing power limitations, which inherently exist in a typical multi-sensor real-world robotic application. To efficiently recognise the environment under these two limitations, attention of an intelligent agent is controlled by employing the reinforcement learning framework. We propose an estimation method using estimated mixture-of-experts task and attention learning in perceptual space. An agent learns how to employ its sensory resources, and when to stop observing, by estimating its perceptual... (More)
The main goal of this paper is modelling attention while using it in efficient path planning of mobile robots. The key challenge in concurrently aiming these two goals is how to make an optimal, or near-optimal, decision in spite of time and processing power limitations, which inherently exist in a typical multi-sensor real-world robotic application. To efficiently recognise the environment under these two limitations, attention of an intelligent agent is controlled by employing the reinforcement learning framework. We propose an estimation method using estimated mixture-of-experts task and attention learning in perceptual space. An agent learns how to employ its sensory resources, and when to stop observing, by estimating its perceptual space. In this paper, static estimation of the state space in a learning task problem, which is examined in the WebotsTM simulator, is performed. Simulation results show that a robot learns how to achieve an optimal policy with a controlled cost by estimating the state space instead of continually updating sensory information. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Attention Control, State Estimation, Bayesian Reinforcement Learning, Decision Making, Mixture of Experts
in
International Journal of Systems Science
volume
47
issue
7
pages
1659 - 1674
publisher
Taylor & Francis
external identifiers
  • scopus:85000195459
ISSN
0020-7721
DOI
10.1080/00207721.2014.945982
language
English
LU publication?
yes
id
f8c1e605-1ddd-47bd-974c-fcca4966c51a
date added to LUP
2017-05-15 17:10:57
date last changed
2017-07-09 05:00:58
@article{f8c1e605-1ddd-47bd-974c-fcca4966c51a,
  abstract     = {The main goal of this paper is modelling attention while using it in efficient path planning of mobile robots. The key challenge in concurrently aiming these two goals is how to make an optimal, or near-optimal, decision in spite of time and processing power limitations, which inherently exist in a typical multi-sensor real-world robotic application. To efficiently recognise the environment under these two limitations, attention of an intelligent agent is controlled by employing the reinforcement learning framework. We propose an estimation method using estimated mixture-of-experts task and attention learning in perceptual space. An agent learns how to employ its sensory resources, and when to stop observing, by estimating its perceptual space. In this paper, static estimation of the state space in a learning task problem, which is examined in the WebotsTM simulator, is performed. Simulation results show that a robot learns how to achieve an optimal policy with a controlled cost by estimating the state space instead of continually updating sensory information.},
  author       = {Gharaee, Zahra and Fatehi, Alireza and Mirian, Maryam  and Nili Ahmadabadi, Majid},
  issn         = {0020-7721},
  keyword      = {Attention Control,State Estimation,Bayesian Reinforcement Learning,Decision Making,Mixture of Experts},
  language     = {eng},
  month        = {08},
  number       = {7},
  pages        = {1659--1674},
  publisher    = {Taylor & Francis},
  series       = {International Journal of Systems Science},
  title        = {Attention control learning in the decision space using state estimation},
  url          = {http://dx.doi.org/10.1080/00207721.2014.945982},
  volume       = {47},
  year         = {2014},
}