SS-MAIL: Self-Supervised Multi-Agent Imitation Learning.

Akshay Dharmavaram Tejus Gupta Jiachen Li Katia P. Sycara

Published in: CoRR (2021)

Keyphrases

imitation learning
multi agent
reinforcement learning
email
robotic systems
maximum margin
humanoid robot
multi agent systems
function approximation
machine learning
computer vision
reinforcement learning methods
model free
control problems
markov logic
relational domains