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

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

Published in: CoRR (2020)

Keyphrases

inverse reinforcement learning
bayesian nonparametric
partially observable environments
preference elicitation
reward function
state variables
state space
decision problems