Patrick F. Riley's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

Layered Disclosure: Revealing Agents' Internals

Patrick Riley, Peter Stone, and Manuela Veloso. Layered Disclosure: Revealing Agents' Internals. In C. Castelfranchi and Y. Lespérance, editors, Intelligent Agents VII. Agent Theories, Architectures, and Languages --- 7th. International Workshop, ATAL-2000, Boston, MA, USA, July 7--9, 2000, Proceedings, number 1986 in Lecture Notes in Artificial Intelligence, pp. 61–72, Springer, Berlin, 2001.
Publisher's Webpage© Springer-Verlag

Download

[PDF]280.1kB  [gzipped postscript]177.4kB  

Abstract

A perennial challenge in creating and using complex autonomous agents is following their choices of actions as the world changes dynamically and understanding why they act as they do. This paper reports on our work to support human developers and observers to better follow and understand the actions of autonomous agents. We introduce the concept of layered disclosure by which autonomous agents have included in their architecture the foundations necessary to allow them to disclose upon request the specific reasons for their actions. Layered disclosure hence goes beyond standard plain code debugging tools. In its essence it also gives the agent designer the ability to define an appropriate information hierarchy, which can include agent-specific constructs such as internal state that persists over time. The user may request this information at any of the specified levels of detail, and either retroactively or while the agent is acting. We present layered disclosure as we created and implemented it in the simulated robotic soccer domain. We contribute the detailed and principled design to support the application of layered disclosure to other agent domains. Layered disclosure played an important role in our successful development of the RoboCup undefeated champion \mboxCMUnited-99 multiagent team.

BibTeX

@incollection(ATAL-LD,
  author =	 {Patrick Riley and Peter Stone and Manuela Veloso},
  title =	 {Layered Disclosure: Revealing Agents' Internals},
  booktitle =	 {Intelligent Agents VII. Agent Theories,
                  Architectures, and Languages --- 7th.~International
                  Workshop, ATAL-2000, Boston, MA, USA, July 7--9,
                  2000, Proceedings},
  editor =	 "C.~Castelfranchi and Y.~Lesp\'{e}rance",
  publisher =	 "Springer",
  address =	 {Berlin},
  series =	 "Lecture Notes in Artificial Intelligence",
  number = 	 {1986},
  pages = 	 {61--72},
  year =	 2001,
  wwwnote =      {<a href="http://www.springer.de/comp/lncs/index.html">Publisher's Webpage</a>&copy Springer-Verlag},
  abstract =	 {A perennial challenge in creating and using complex
                  autonomous agents is following their choices of
                  actions as the world changes dynamically and
                  understanding why they act as they do. This paper
                  reports on our work to support human developers and
                  observers to better follow and understand the
                  actions of autonomous agents. We introduce the
                  concept of {\it layered disclosure} by which
                  autonomous agents have included in their
                  architecture the foundations necessary to allow them
                  to disclose upon request the specific reasons for
                  their actions. Layered disclosure hence goes beyond
                  standard plain code debugging tools. In its essence
                  it also gives the agent designer the ability to
                  define an appropriate information hierarchy, which
                  can include agent-specific constructs such as
                  internal state that persists over time. The user may
                  request this information at any of the specified
                  levels of detail, and either retroactively or while
                  the agent is acting. We present layered disclosure
                  as we created and implemented it in the simulated
                  robotic soccer domain. We contribute the detailed
                  and principled design to support the application of
                  layered disclosure to other agent domains. Layered
                  disclosure played an important role in our
                  successful development of the RoboCup undefeated
                  champion \mbox{CMUnited-99} multiagent team. },
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Other},
  bib2html_funding = {CoABS,ActiveTemplates},
)

Generated by bib2html.pl (written by Patrick Riley ) on Thu Mar 31, 2005 16:21:00