Inverse Reinforcement Learning with Missing Data.

Tien Mai Quoc Phong Nguyen Kian Hsiang Low Patrick Jaillet

Published in: CoRR (2019)

Keyphrases

missing data
inverse reinforcement learning
preference elicitation
reward function
missing values
low rank
incomplete data
multiple imputation
temporal difference
np hard
state space
semi supervised
random walk
markov decision processes