EUVIMEDEUVIMED entdecken
Crossref

Effective Exploration via Intrinsic Motivation in Reinforcement Learning

Berkay Eren, Alper Demir

Journal of Advanced Research in Natural and Applied Sciences · 30.06.2026 · 12 (2) · 171-192

DOI: 10.28979/jarnas.1922504 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Advanced Research in Natural and Applied Sciences, online erschienen am 30.06.2026. Verfasst von Berkay Eren und 1 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reinforcement learning agents often struggle in sparse-reward environments where feedback is limited and appears only after a sequence of correct actions. In partialobservable navigation tasks, simple exploration strategies are often insufficient. This study investigates intrinsic motivation mechanisms, specifically focusing on the “Don’t Do What Doesn’t Matter” (DoWhaM) method, which rewards rare but effective actions. To address its limitations in spatial tasks, we propose Area-aware DoWhaM Adaptation (ADA). This method extends action-usefulness with spatial novelty bonuses to encourage expanding the visible area. We evaluate ADA against DoWhaM and a Count-Based baselines in various MiniGrid environments. Results indicate that ADA improves sample efficiency in the early stages of training. In dynamic environments where the layout changes in every episode, ADA significantly outperforms the Count-Based baseline and learns faster than DoWhaM. These findings suggest that combining action-usefulness with spatial novelty provides a robust heuristic for exploration in procedurally generated tasks.

Zitieren

APA

Eren, B., & Demir, A. (2026). Effective Exploration via Intrinsic Motivation in Reinforcement Learning. Journal of Advanced Research in Natural and Applied Sciences, 12(2), 171-192. https://doi.org/10.28979/jarnas.1922504

Vancouver

Eren B, Demir A. Effective Exploration via Intrinsic Motivation in Reinforcement Learning. Journal of Advanced Research in Natural and Applied Sciences. 2026;12(2):171-192. doi:10.28979/jarnas.1922504

BibTeX
@article{Eren2026,
  author = {Eren, Berkay and Demir, Alper},
  title = {Effective Exploration via Intrinsic Motivation in Reinforcement Learning},
  journal = {Journal of Advanced Research in Natural and Applied Sciences},
  year = {2026},
  volume = {12},
  number = {2},
  pages = {171--192},
  doi = {10.28979/jarnas.1922504}
}
Kostenlos starten →