@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{AAAIsymp09-knox,
 author="W.\ Bradley Knox and Ian Fasel and Peter Stone",
 title="Design Principles for Creating Human-Shapable Agents",
 booktitle="AAAI Spring 2009 Symposium on Agents that Learn from Human Teachers",
 month="March",
 year="2009",
 abstract={In order for learning agents to be useful to non-technical users, it
  is important to be able to teach agents how to perform new tasks using
  simple communication methods. We begin this paper by describing a
  framework we recently developed called Training an Agent Manually via
  Evaluative Reinforcement (TAMER), which allows a human to train a
  learning agent by giving simple scalar reinforcement\footnote{In this
  paper, we distinguish between human reinforcement and environmental
  reward within an MDP. To avoid confusion, human feedback is always
  called ``reinforcement''.} signals while observing the agent perform
  the task. We then discuss how this work fits into a general taxonomy
  of methods for human-teachable (HT) agents and argue that the entire
  field of HT agents could benefit from an increased focus on the {\em
  human} side of teaching interactions.  We then propose a set of
  conjectures about aspects of human teaching behavior that we believe
  could be incorporated into future work on HT agents.},
 wwwnote={<a href="http://www.aaai.org/Symposia/Spring/sss09.php">AAAI Spring 2009 Symposium: Agents that Learn from Human Teachers</a>},
}