ARC - Actor Residual Critic for Adversarial Imitation Learning.

Ankur Deka Changliu Liu Katia P. Sycara

Published in: CoRR (2022)

Keyphrases

imitation learning
reinforcement learning
humanoid robot
maximum margin
robotic systems
multi agent
temporal difference
active learning
reinforcement learning algorithms
reinforcement learning methods
function approximation
relational domains