English

Enhancing Agent Communication and Learning through Action and Language

Artificial Intelligence 2023-09-28 v3 Machine Learning

Abstract

We introduce a novel category of GC-agents capable of functioning as both teachers and learners. Leveraging action-based demonstrations and language-based instructions, these agents enhance communication efficiency. We investigate the incorporation of pedagogy and pragmatism, essential elements in human communication and goal achievement, enhancing the agents' teaching and learning capabilities. Furthermore, we explore the impact of combining communication modes (action and language) on learning outcomes, highlighting the benefits of a multi-modal approach.

Keywords

Cite

@article{arxiv.2308.10842,
  title  = {Enhancing Agent Communication and Learning through Action and Language},
  author = {Hugo Caselles-Dupré and Olivier Sigaud and Mohamed Chetouani},
  journal= {arXiv preprint arXiv:2308.10842},
  year   = {2023}
}

Comments

IMOL workshop, Paris 2023

R2 v1 2026-06-28T12:00:37.554Z