@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{ICDL08-knox,
 author="W.\ Bradley Knox and Peter Stone",
 title="TAMER: Training an Agent Manually via Evaluative Reinforcement",
 booktitle="IEEE 7th International Conference on Development and Learning",
 month="August",
 year="2008",
 abstract={Though computers have surpassed humans at many tasks, especially
  computationally intensive ones, there are many tasks for which human
  expertise remains necessary and/or useful.  For such tasks, it is
  desirable for a human to be able to transmit knowledge to a learning
  agent as quickly and effortlessly as possible, and, ideally, without
  any knowledge of the details of the agent's learning process.  This
  paper proposes a general framework called Training an Agent
  Manually via Evaluative Reinforcement (TAMER) that allows a human to
  train a learning agent to perform a common class of complex tasks
  simply by giving scalar reward signals in response to the agent's
  observed actions.  Specifically, in sequential decision making tasks,
  an agent models the human's reward function and chooses actions that
  it predicts will receive the most reward.  Our novel algorithm is
  fully implemented and tested on the game Tetris.  Leveraging the human
  trainers' feedback, the agent learns to clear an average of more than
  50 lines by its third game, an order of magnitude faster than the best
  autonomous learning agents.},
 wwwnote={<a href="http://www.icdl08.org/">ICDL-2008</a>},
}