EUVIMEDEUVIMED entdecken
Crossref

Memory Based Advantage Shaping for LLM-Guided Reinforcement Learning (Student Abstract)

Narjes Nourzad, Carlee Joe-Wong

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41337-41339

DOI: 10.1609/aaai.v40i48.42261 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Narjes Nourzad und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for subgoal discovery and trajectory guidance. While LLMs can support exploration, frequent reliance on LLM calls raises concerns about scalability and reliability. We address these challenges by constructing a memory graph that encodes subgoals and trajectories from both LLM guidance and the agent’s own successful rollouts. From this graph, we derive a utility function that evaluates how closely the agent’s trajectories align with prior successful strategies. This utility shapes the advantage function, providing the critic with additional guidance without altering the reward. Our method relies primarily on offline input and only occasional online queries, avoiding dependence on continuous LLM supervision. Preliminary experiments in benchmark environments show improved sample efficiency and faster early learning compared to baseline RL methods, with final returns comparable to methods that require frequent LLM interaction.

Zitieren

APA

Nourzad, N., & Joe-Wong, C. (2026). Memory Based Advantage Shaping for LLM-Guided Reinforcement Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41337-41339. https://doi.org/10.1609/aaai.v40i48.42261

Vancouver

Nourzad N, Joe-Wong C. Memory Based Advantage Shaping for LLM-Guided Reinforcement Learning (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41337-41339. doi:10.1609/aaai.v40i48.42261

BibTeX
@article{Nourzad2026,
  author = {Nourzad, Narjes and Joe-Wong, Carlee},
  title = {Memory Based Advantage Shaping for LLM-Guided Reinforcement Learning (Student Abstract)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41337--41339},
  doi = {10.1609/aaai.v40i48.42261}
}
Kostenlos starten →