Hierarchical extreme learning machine based reinforcement learning for goal localization
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 process...
| Main Authors: | , , |
|---|---|
| Format: | Proceeding Paper |
| Language: | English English |
| Published: |
IOP Publishing
2017
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/54838/ http://irep.iium.edu.my/54838/2/54838-edited.pdf http://irep.iium.edu.my/54838/1/54838-Hierarchical%20extreme%20learning%20machine%20based%20reinforcement%20learning%20for%20goal%20localization_SCOPUS.pdf |
| _version_ | 1848784476572745728 |
|---|---|
| author | AlDahoul, Nouar Htike, Zaw Zaw Akmeliawati, Rini |
| author_facet | AlDahoul, Nouar Htike, Zaw Zaw Akmeliawati, Rini |
| author_sort | AlDahoul, Nouar |
| building | IIUM Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-14T16:37:51Z |
| format | Proceeding Paper |
| id | iium-54838 |
| institution | International Islamic University Malaysia |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-14T16:37:51Z |
| publishDate | 2017 |
| publisher | IOP Publishing |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | iium-548382017-06-05T02:40:27Z http://irep.iium.edu.my/54838/ Hierarchical extreme learning machine based reinforcement learning for goal localization AlDahoul, Nouar Htike, Zaw Zaw Akmeliawati, Rini T Technology (General) TL500 Aeronautics 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. IOP Publishing 2017 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/54838/2/54838-edited.pdf application/pdf en http://irep.iium.edu.my/54838/1/54838-Hierarchical%20extreme%20learning%20machine%20based%20reinforcement%20learning%20for%20goal%20localization_SCOPUS.pdf 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. http://iopscience.iop.org/article/10.1088/1757-899X/184/1/012055/pdf 10.1088/1757-899X/184/1/012055 |
| spellingShingle | T Technology (General) TL500 Aeronautics AlDahoul, Nouar Htike, Zaw Zaw Akmeliawati, Rini Hierarchical extreme learning machine based reinforcement learning for goal localization |
| title | Hierarchical extreme learning machine based reinforcement
learning for goal localization |
| title_full | Hierarchical extreme learning machine based reinforcement
learning for goal localization |
| title_fullStr | Hierarchical extreme learning machine based reinforcement
learning for goal localization |
| title_full_unstemmed | Hierarchical extreme learning machine based reinforcement
learning for goal localization |
| title_short | Hierarchical extreme learning machine based reinforcement
learning for goal localization |
| title_sort | hierarchical extreme learning machine based reinforcement
learning for goal localization |
| topic | T Technology (General) TL500 Aeronautics |
| url | http://irep.iium.edu.my/54838/ http://irep.iium.edu.my/54838/ http://irep.iium.edu.my/54838/ http://irep.iium.edu.my/54838/2/54838-edited.pdf http://irep.iium.edu.my/54838/1/54838-Hierarchical%20extreme%20learning%20machine%20based%20reinforcement%20learning%20for%20goal%20localization_SCOPUS.pdf |