Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Potential-based reward shaping using state–space segmentation for efficiency in reinforcement learning
Date
2024-08-01
Author
Bal, Melis İlayda
Aydın, Hüseyin
İyigün, Cem
Polat, Faruk
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
103
views
0
downloads
Cite This
Reinforcement Learning (RL) algorithms encounter slow learning in environments with sparse explicit reward structures due to the limited feedback available on the agent's behavior. This problem is exacerbated particularly in complex tasks with large state and action spaces. To address this inefficiency, in this paper, we propose a novel approach based on potential-based reward-shaping using state–space segmentation to decompose the task and to provide more frequent feedback to the agent. Our approach involves extracting state–space segments by formulating the problem as a minimum cut problem on a transition graph, constructed using the agent's experiences during interactions with the environment via the Extended Segmented Q-Cut algorithm. Subsequently, these segments are leveraged in the agent's learning process through potential-based reward shaping. Our experimentation on benchmark problem domains with sparse rewards demonstrated that our proposed method effectively accelerates the agent's learning without compromising computation time while upholding the policy invariance principle.
Subject Keywords
Potential-based reward shaping
,
Reinforcement learning
,
Reward shaping
,
Sparse rewards
,
State–space segmentation
URI
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85190141334&origin=inward
https://hdl.handle.net/11511/109361
Journal
Future Generation Computer Systems
DOI
https://doi.org/10.1016/j.future.2024.03.057
Collections
Department of Computer Engineering, Article
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
M. İ. Bal, H. Aydın, C. İyigün, and F. Polat, “Potential-based reward shaping using state–space segmentation for efficiency in reinforcement learning,”
Future Generation Computer Systems
, vol. 157, pp. 469–484, 2024, Accessed: 00, 2024. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85190141334&origin=inward.