Evaluating the Perceived Safety of Urban City via Maximum Entropy Deep Inverse Reinforcement Learning.

Yaxuan Wang Zhixin Zeng Qijun Zhao

Published in: CoRR (2022)

Keyphrases

maximum entropy
inverse reinforcement learning
maximum entropy principle
preference elicitation
markov models
conditional random fields
pairwise
generative model
minimum cross entropy
reinforcement learning
markov random field
temporal difference