Augmenting decision with hypothesis in reinforcement learning
Value-based reinforcement learning is the current State-Of-The-Art due to high sampling efficiency. However, our study shows it suffers from low exploitation in early training period and bias sensitiveness. To address these issues, we propose to augment the decision-making process with hypothesis, a...
Saved in:
Main Authors: | NGUYEN, Minh Quang, LAUW, Hady Wirawan |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9842 https://ink.library.smu.edu.sg/context/sis_research/article/10842/viewcontent/icml24.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Reinforcement learning for sequential decision making with constraints
by: LING, Jiajing
Published: (2023) -
Configurable mirror descent : Towards a unification of decision making
by: LI, Pengdeng, et al.
Published: (2024) -
Constrained reinforcement learning in hard exploration problems
by: PATHMANATHAN, Pankayaraj, et al.
Published: (2023) -
Integrating motivated learning and k-winner-take-all to coordinate multi-agent reinforcement learning
by: TENG, Teck-Hou, et al.
Published: (2014) -
Imitate the good and avoid the bad: An incremental approach to safe reinforcement learning
by: HOANG, Minh Huy, et al.
Published: (2024)