Login / Signup
LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation.
Geon-Hyeong Kim
Jongmin Lee
Youngsoo Jang
Hongseok Yang
Kee-Eung Kim
Published in:
NeurIPS (2022)
Keyphrases
</>
stationary distribution
markov chain
neural network
reinforcement learning
random walk
learning algorithm
optimal solution