Multi-Agent Generative Adversarial Imitation Learning.

Jiaming Song Hongyu Ren Dorsa Sadigh Stefano Ermon

Published in: ICLR (Workshop) (2018)

Keyphrases

multi agent
imitation learning
reinforcement learning
maximum margin
multi agent systems
robotic systems
humanoid robot
generative model
single agent
multiple agents
reinforcement learning methods
learning algorithm
real time
state space
markov random field