@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{NeurIPS2021-Guo,
  author = {Sihang Guo and Ruohan Zhang and Bo Liu and Yifeng Zhu and Mary Hayhoe and Dana Ballard and Peter Stone},
  title = {Machine versus Human Attention in Deep Reinforcement Learning Tasks},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  location = {Virtual Only},
  month = {December},
  year = {2021},
  abstract = {
Deep reinforcement learning (RL) algorithms are powerful tools for solving
visuomotor decision tasks. However, the trained models are often difficult
to interpret, because they are represented as end-to-end deep neural
networks. In this paper, we shed light on the inner workings of such
trained models by analyzing the pixels that they attend to during task 
execution, and comparing them with the pixels attended to by humans 
executing the same tasks. To this end, we investigate the following 
two questions that, to the best of our knowledge, have not been previously 
studied. 1) How similar are the visual representations learned by RL agents 
and humans when performing the same task? and, 2) How do similarities 
and differences in these learned representations explain RL agents’ 
performance on these tasks? Specifically, we compare the saliency 
maps of RL agents against visual attention models of human experts when 
learning to play Atari games. Further, we analyze how hyperparameters of 
the deep RL algorithm affect the learned representations and saliency maps 
of the trained agents. The insights provided have the potential to inform 
novel algorithms for closing the performance gap between human experts and 
RL agents.
  },
}