EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Task Execution and Interactive Learning of Embodied Agents in Complex Open Environments

Julian Westwood, Noah Holmgren

Fundamental Scientific Reports in Multidisciplinary Areas · 15.04.2026 · 2 (1) · 130-140

DOI: 10.66238/fsrma62 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fundamental Scientific Reports in Multidisciplinary Areas, online erschienen am 15.04.2026. Verfasst von Julian Westwood und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The deployment of embodied artificial intelligence in complex, open-ended environments requires agents capable of robust task execution and continuous adaptation. Traditional reinforcement learning paradigms often falter when faced with infinite state spaces, novel object properties, and sparse reward signals inherent to unstructured real-world domains. This paper presents a comprehensive framework for task execution and interactive learning designed to enhance the sample efficiency and generalization capabilities of embodied agents. We formalize the interactive learning process within a Partially Observable Markov Decision Process and introduce a multimodal representation learning architecture that integrates environmental perception with active interaction mechanisms. By dynamically querying external knowledge sources or human supervisors when uncertainty thresholds are exceeded, the agent mitigates the risks of catastrophic failure and reduces the sample complexity of exploration. Our methodological contributions include an uncertainty-aware policy optimization algorithm and a memory-augmented state representation module that processes sequential observations to infer latent environmental dynamics. Extensive empirical evaluations conducted in procedurally generated three-dimensional simulators demonstrate that our proposed interactive learning approach significantly outperforms conventional deep reinforcement learning baselines in terms of task success rate, average episode length, and overall sample efficiency. The findings suggest that integrating active interaction modalities into the foundational learning loops of embodied agents is critical for bridging the gap between constrained simulated environments and dynamic open-world deployments.

Zitieren

APA

Westwood, J., & Holmgren, N. (2026). Task Execution and Interactive Learning of Embodied Agents in Complex Open Environments. Fundamental Scientific Reports in Multidisciplinary Areas, 2(1), 130-140. https://doi.org/10.66238/fsrma62

Vancouver

Westwood J, Holmgren N. Task Execution and Interactive Learning of Embodied Agents in Complex Open Environments. Fundamental Scientific Reports in Multidisciplinary Areas. 2026;2(1):130-140. doi:10.66238/fsrma62

BibTeX
@article{Westwood2026,
  author = {Westwood, Julian and Holmgren, Noah},
  title = {Task Execution and Interactive Learning of Embodied Agents in Complex Open Environments},
  journal = {Fundamental Scientific Reports in Multidisciplinary Areas},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {130--140},
  doi = {10.66238/fsrma62}
}
Kostenlos starten →