Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Deep TAMER: Interactive agent shaping in high-dimensional state spaces

Garrett Warnell, Nicholas Waytowich, Vernon Lawhern, and Peter Stone. Deep TAMER: Interactive agent shaping in high-dimensional state spaces. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, February 2018.

Download

[PDF]1.6MB  [slides.pptx]16.2MB  

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.

BibTeX Entry

@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.
    }
}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Aug 19, 2019 13:01:01