Masking and Demasking Agents
Reinforcement
Observational Learning
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: May 6, 2026

The HoneyComb Paradigm for Research on Collective Human Behavior
Published on: January 19, 2019
Hend Khalid Alkahtani1, Ybytayeva Galiya2, Bekarystankyzy Akbayan3
1Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, 11671, Saudi Arabia.
This study introduces an Explainable Multi-Agent Reinforcement Learning (EMARL) framework for secure and interpretable Unmanned Aerial Vehicle (UAV) swarm communications. The EMARL system enhances packet delivery, accuracy, and efficiency while reducing delay and false positives, even under attacks.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: