Relational Q-Functionals: Multi-Agent Learning to Recover from Unforeseen Robot Malfunctions in Continuous Action Domains

• Published in: 2024 21st International Conference on Ubiquitous Robots (UR) pp. 251 - 256
• Main Authors: Findik, Yasin, Robinette, Paul, Jerath, Kshitij, Azadeh, Reza
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24.06.2024
• Subjects: Learning systems; Legged locomotion; Multi-agent systems; Resilience; Robot kinematics; Task analysis

Cooperative multi-agent learning methods are essential in developing effective cooperation strategies in multi-agent domains. In robotics, these methods extend beyond multi-robot scenarios to single-robot systems, where they enable coordination among different robot modules (e.g., robot legs or join...