Sökning: onr:"swepub:oai:lup.lub.lu.se:f8c1e605-1ddd-47bd-974c-fcca4966c51a" >
Attention control l...
Attention control learning in the decision space using state estimation
-
- Gharaee, Zahra (författare)
- Lund University,Lunds universitet,Kognitiv modellering,Forskargrupper vid Lunds universitet,Kognitionsvetenskap,Filosofiska institutionen,Institutioner,Humanistiska och teologiska fakulteterna,Cognitive modeling,Lund University Research Groups,Cognitive Science,Department of Philosophy,Departments,Joint Faculties of Humanities and Theology
-
- Fatehi, Alireza (författare)
- K. N. Toosi University of Technology
-
- Mirian, Maryam (författare)
- University of Tehran
-
visa fler...
-
- Nili Ahmadabadi, Majid (författare)
- University of Tehran
-
visa färre...
-
(creator_code:org_t)
- 2014-08-08
- 2014
- Engelska.
-
Ingår i: International Journal of Systems Science. - : Informa UK Limited. - 0020-7721 .- 1464-5319. ; 47:7, s. 1659-1674
- Relaterad länk:
-
http://dx.doi.org/10...
-
visa fler...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- HUMANIORA -- Filosofi, etik och religion -- Filosofi (hsv//swe)
- HUMANITIES -- Philosophy, Ethics and Religion -- Philosophy (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)
Nyckelord
- Attention Control
- State Estimation
- Bayesian Reinforcement Learning
- Decision Making
- Mixture of Experts
Publikations- och innehållstyp
- art (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas