IIUM Repository (IREP)

Hierarchical extreme learning machine based reinforcement learning for goal localization

AlDahoul, Nouar and Htike, Zaw Zaw and Akmeliawati, Rini (2017) Hierarchical extreme learning machine based reinforcement learning for goal localization. In: 3rd International Conference on Mechanical, Automotive and Aerospace Engineering 2016 (ICMAAE’16), 25th-27th July 2016, Kuala Lumpur, Malaysia.

[img] PDF - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy
[img] PDF (SCOPUS)
Restricted to Registered users only

Download (72kB) | Request a copy

Abstract

The objective of goal localization is to find the location of goals in noisy environments. Simple actions are performed to move the agent towards the goal. The goal detector should be capable of minimizing the error between the predicted locations and the true ones. Few regions need to be processed by the agent to reduce the computational effort and increase the speed of convergence. In this paper, reinforcement learning (RL) method was utilized to find optimal series of actions to localize the goal region. The visual data, a set of images, is high dimensional unstructured data and needs to be represented efficiently to get a robust detector. Different deep Reinforcement models have already been used to localize a goal but most of them take long time to learn the model. This long learning time results from the weights fine tuning stage that is applied iteratively to find an accurate model. Hierarchical Extreme Learning Machine (H-ELM) was used as a fast deep model that doesn’t fine tune the weights. In other words, hidden weights are generated randomly and output weights are calculated analytically. H-ELM algorithm was used in this work to find good features for effective representation. This paper proposes a combination of Hierarchical Extreme learning machine and Reinforcement learning to find an optimal policy directly from visual input. This combination outperforms other methods in terms of accuracy and learning speed. The simulations and results were analysed by using MATLAB.

Item Type: Conference or Workshop Item (Plenary Papers)
Additional Information: 6919/54838
Uncontrolled Keywords: aerospace engineering,iIterative methods, knowledge acquisition, learning systems, MATLAB
Subjects: T Technology > T Technology (General)
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL500 Aeronautics
Kulliyyahs/Centres/Divisions/Institutes: Kulliyyah of Engineering > Department of Mechatronics Engineering
Depositing User: Dr. Zaw Zaw Htike
Date Deposited: 05 Jun 2017 10:40
Last Modified: 05 Jun 2017 10:40
URI: http://irep.iium.edu.my/id/eprint/54838

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year