Login / Signup
Relational Q-Functionals: Multi-Agent Learning to Recover from Unforeseen Robot Malfunctions in Continuous Action Domains.
Yasin Findik
Paul Robinette
Kshitij Jerath
Reza Azadeh
Published in:
UR (2024)
Keyphrases
</>
multi agent learning
complex domains
continuous action
game theory
mobile robot
multi agent
robot navigation
cooperative
continuous state
artificial intelligence
reinforcement learning
path planning
policy search
neural network
computational complexity
autonomous robots