@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{AAAI18-Warnell,
  author = {Garrett Warnell and Nicholas Waytowich and Vernon Lawhern and Peter Stone},
  title = {{Deep TAMER: Interactive agent shaping in high-dimensional state spaces}},
  booktitle = {Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
  location = {New Orleans, Louisiana, USA},
  month = {February},
  year = {2018},
  abstract={
    While recent advances in deep reinforcement learning have allowed 
    autonomous learning agents to succeed at a variety of complex tasks, 
    existing algorithms generally require a lot of training data. One way to 
    increase the speed at which agents are able to learn to perform tasks is 
    by leveraging the input of human trainers. Although such input can take 
    many forms, real-time, scalar-valued feedback is especially useful in 
    situations where it proves difficult or impossible for humans to provide 
    expert demonstrations. Previous approaches have shown the usefulness of 
    human input provided in this fashion (e.g., the TAMER framework), but they 
    have thus far not considered high-dimensional state spaces or employed 
    the use of deep learning. In this paper, we do both: we propose Deep 
    TAMER, an extension of the TAMER framework that leverages the 
    representational power of deep neural networks in order to learn complex 
    tasks in just a short amount of time with a human trainer. We demonstrate 
    Deep TAMER’s success by using it and just 15 minutes of human-provided 
    feedback to train an agent that performs better than humans on the Atari 
    game of BOWLING - a task that has proven difficult for even 
    state-of-the-art reinforcement learning methods.
    }
}