Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/89871
Title: | Probabilistic guided exploration for reinforcement learning in self-organizing neural networks | Authors: | Wang, Peng Zhou, Weigui Jair Wang, Di Tan, Ah-Hwee |
Keywords: | Reinforcement Learning Self-organizing Neural Networks Engineering::Computer science and engineering |
Issue Date: | 2018 | Source: | Wang, P., Zhou, W. J., Wang, D., & Tan, A.-H. (2018). Probabilistic guided exploration for reinforcement learning in self-organizing neural networks. 2018 IEEE International Conference on Agents (ICA). doi:10.1109/agents.2018.8460067 | Conference: | 2018 IEEE International Conference on Agents (ICA) | Abstract: | Exploration is essential in reinforcement learning, which expands the search space of potential solutions to a given problem for performance evaluations. Specifically, carefully designed exploration strategy may help the agent learn faster by taking the advantage of what it has learned previously. However, many reinforcement learning mechanisms still adopt simple exploration strategies, which select actions in a pure random manner among all the feasible actions. In this paper, we propose novel mechanisms to improve the existing knowledge-based exploration strategy based on a probabilistic guided approach to select actions. We conduct extensive experiments in a Minefield navigation simulator and the results show that our proposed probabilistic guided exploration approach significantly improves the convergence rate. | URI: | https://hdl.handle.net/10356/89871 http://hdl.handle.net/10220/49724 |
DOI: | 10.1109/agents.2018.8460067 | Schools: | School of Computer Science and Engineering | Rights: | © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/agents.2018.8460067 | Fulltext Permission: | open | Fulltext Availability: | With Fulltext |
Appears in Collections: | SCSE Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ICA2018MineField.pdf | 392.25 kB | Adobe PDF | View/Open |
SCOPUSTM
Citations
50
5
Updated on Mar 22, 2024
Page view(s) 50
429
Updated on Mar 27, 2024
Download(s) 50
102
Updated on Mar 27, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.