Evaluating the perceived safety of urban city via maximum entropy deep inverse reinforcement learning

Yaxuan Wang, Zhixin Zeng, Qijun Zhao
Proceedings of The 14th Asian Conference on Machine Learning, PMLR 189:1085-1100, 2023.

Abstract

Inspired by expert evaluation policy for urban perception, we proposed a novel inverse reinforcement learning (IRL) based framework for predicting urban safety and recovering the corresponding reward function. We also presented a scalable state representation method to model the prediction problem as a Markov decision process (MDP) and use reinforcement learning (RL) to solve the problem. Additionally, we built a dataset called SmallCity based on the crowdsourcing method to conduct the research. As far as we know, this is the first time the IRL approach has been introduced to the urban safety perception and planning field to help experts quantitatively analyze perceptual features. Our results showed that IRL has promising prospects in this field. We will later open-source the crowdsourcing data collection site and the model proposed in this paper.

Cite this Paper


BibTeX
@InProceedings{pmlr-v189-wang23c, title = {Evaluating the perceived safety of urban city via maximum entropy deep inverse reinforcement learning}, author = {Wang, Yaxuan and Zeng, Zhixin and Zhao, Qijun}, booktitle = {Proceedings of The 14th Asian Conference on Machine Learning}, pages = {1085--1100}, year = {2023}, editor = {Khan, Emtiyaz and Gonen, Mehmet}, volume = {189}, series = {Proceedings of Machine Learning Research}, month = {12--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v189/wang23c/wang23c.pdf}, url = {https://proceedings.mlr.press/v189/wang23c.html}, abstract = {Inspired by expert evaluation policy for urban perception, we proposed a novel inverse reinforcement learning (IRL) based framework for predicting urban safety and recovering the corresponding reward function. We also presented a scalable state representation method to model the prediction problem as a Markov decision process (MDP) and use reinforcement learning (RL) to solve the problem. Additionally, we built a dataset called SmallCity based on the crowdsourcing method to conduct the research. As far as we know, this is the first time the IRL approach has been introduced to the urban safety perception and planning field to help experts quantitatively analyze perceptual features. Our results showed that IRL has promising prospects in this field. We will later open-source the crowdsourcing data collection site and the model proposed in this paper.} }
Endnote
%0 Conference Paper %T Evaluating the perceived safety of urban city via maximum entropy deep inverse reinforcement learning %A Yaxuan Wang %A Zhixin Zeng %A Qijun Zhao %B Proceedings of The 14th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Emtiyaz Khan %E Mehmet Gonen %F pmlr-v189-wang23c %I PMLR %P 1085--1100 %U https://proceedings.mlr.press/v189/wang23c.html %V 189 %X Inspired by expert evaluation policy for urban perception, we proposed a novel inverse reinforcement learning (IRL) based framework for predicting urban safety and recovering the corresponding reward function. We also presented a scalable state representation method to model the prediction problem as a Markov decision process (MDP) and use reinforcement learning (RL) to solve the problem. Additionally, we built a dataset called SmallCity based on the crowdsourcing method to conduct the research. As far as we know, this is the first time the IRL approach has been introduced to the urban safety perception and planning field to help experts quantitatively analyze perceptual features. Our results showed that IRL has promising prospects in this field. We will later open-source the crowdsourcing data collection site and the model proposed in this paper.
APA
Wang, Y., Zeng, Z. & Zhao, Q.. (2023). Evaluating the perceived safety of urban city via maximum entropy deep inverse reinforcement learning. Proceedings of The 14th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 189:1085-1100 Available from https://proceedings.mlr.press/v189/wang23c.html.

Related Material