Imitation Learning from Observations under Transition Model Disparity.

Tanmay Gangwani Yuan Zhou Jian Peng

Published in: ICLR (2022)

Keyphrases

transition model
imitation learning
reinforcement learning
robotic systems
maximum margin
humanoid robot
stereo matching
function approximation
reinforcement learning algorithms
markov decision problems
active learning
learning algorithm
optimal solution
generative model
decision theory
state transition