f-IRL: Inverse Reinforcement Learning via State Marginal Matching.

Tianwei Ni Harshit S. Sikchi Yufei Wang Tejus Gupta Lisa Lee Ben Eysenbach

Published in: CoRL (2020)

Keyphrases

inverse reinforcement learning
bayesian nonparametric
partially observable environments
reward function
preference elicitation
state space
temporal difference
machine learning
partially observable