Experience Extractor for Adaptive Tradeoff Between Exploration and Exploitation in Reinforcement Learning
Mathematics · 11.05.2026 · 14 (10) · 1624
DOI: 10.3390/math14101624 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 11.05.2026. Verfasst von Zhi Yi und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Hunan Province, Hunan Provincial Natural Science Foundation Project.
Abstract (Originalsprache)
In Reinforcement Learning (RL), the agent cannot distinguish between exploratory and exploitative experience. Not all sequential experiences contribute equally to the agent’s optimization, and the same experience holds different importance at different learning stages. We propose the Extractor for Adaptive Tradeoff Between Exploration and Exploitation (EATBEE), a task-oriented tool that tightly couples with the agent’s current knowledge and enables adaptive knowledge acquisition. We compare the originally sampled data with the task-driven data distribution to clearly illustrate their deviation. Then, we show how EATBEE identifies and extracts beneficial data for the agent. The monotonic improvement policy is theoretically validated under the assumption that the experience trajectory keeps a high degree of trajectory similarity after extraction. EATBEE serves as an independent module that can be seamlessly integrated with most existing RL algorithms. We substantiate the efficacy and practical applicability of the EATBEE method through experiments conducted in both discrete and continuous environments.
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program of Hunan Province
- Hunan Provincial Natural Science Foundation Project
Zitieren
APA
Yi, Z., Wu, Z., Xie, Y., Chen, M., & Dai, Y. (2026). Experience Extractor for Adaptive Tradeoff Between Exploration and Exploitation in Reinforcement Learning. Mathematics, 14(10), 1624. https://doi.org/10.3390/math14101624
Vancouver
Yi Z, Wu Z, Xie Y, Chen M, Dai Y. Experience Extractor for Adaptive Tradeoff Between Exploration and Exploitation in Reinforcement Learning. Mathematics. 2026;14(10):1624. doi:10.3390/math14101624
BibTeX
@article{Yi2026,
author = {Yi, Zhi and Wu, Zhongmin and Xie, Yongming and Chen, Ming and Dai, Yinglong},
title = {Experience Extractor for Adaptive Tradeoff Between Exploration and Exploitation in Reinforcement Learning},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {10},
pages = {1624},
doi = {10.3390/math14101624}
}
EUVIMED