EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Uncertainty-Aware Continual Reinforcement Learning via PPO with Graph Representation Learning

Dongjae Kim

Mathematics · 08.08.2025 · 13 (16) · 2542

DOI: 10.3390/math13162542 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 08.08.2025. Verfasst von Dongjae Kim. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dankook University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Continual reinforcement learning (CRL) agents face significant challenges when encountering distributional shifts. This paper formalizes these shifts into two key scenarios, namely virtual drift (domain switches), where object semantics change (e.g., walls becoming lava), and concept drift (task switches), where the environment’s structure is reconfigured (e.g., moving from object navigation to a door key puzzle). This paper demonstrates that while conventional convolutional neural networks (CNNs) struggle to preserve relational knowledge during these transitions, graph convolutional networks (GCNs) can inherently mitigate catastrophic forgetting by encoding object interactions through explicit topological reasoning. A unified framework is proposed that integrates GCN-based state representation learning with a proximal policy optimization (PPO) agent. The GCN’s message-passing mechanism preserves invariant relational structures, which diminishes performance degradation during abrupt domain switches. Experiments conducted in procedurally generated MiniGrid environments show that the method significantly reduces catastrophic forgetting in domain switch scenarios. While showing comparable mean performance in task switch scenarios, our method demonstrates substantially lower performance variance (Levene’s test, p

Förderung

  • Dankook University

Zitieren

APA

Kim, D. (2025). Uncertainty-Aware Continual Reinforcement Learning via PPO with Graph Representation Learning. Mathematics, 13(16), 2542. https://doi.org/10.3390/math13162542

Vancouver

Kim D. Uncertainty-Aware Continual Reinforcement Learning via PPO with Graph Representation Learning. Mathematics. 2025;13(16):2542. doi:10.3390/math13162542

BibTeX
@article{Kim2025,
  author = {Kim, Dongjae},
  title = {Uncertainty-Aware Continual Reinforcement Learning via PPO with Graph Representation Learning},
  journal = {Mathematics},
  year = {2025},
  volume = {13},
  number = {16},
  pages = {2542},
  doi = {10.3390/math13162542}
}
Kostenlos starten →