Safe Learning Agents
Papers from 2002 AAAI Spring Symposium
Mike Barley and Hans W. Guesgen, Program Cochairs
Technical Report SS-02-07. Published by The AAAI Press, Menlo Park, California. This technical report is also available in book and CD format.
Please Note: Abstracts are linked to individual titles, and will appear in a separate browser window. Full-text versions of the papers are linked to the abstract text. Access to full text may be restricted to AAAI members. PDF file sizes may be large!
Contents
Safe Learning Agents? Logic-Based Agents! / 1
Eduardo Alonso
User-Agent Value Alignment / 5
Daniel Shapiro and Ross Shachter
Social Pathologies of Adaptive Agents / 13
David Jensen and Victor Lesser
Safe Learning in Mission-Critical Domains: Time is of the Essence / 20
David J. Musliner
Lyapunov Design for Safe Reinforcement Learning Control / 23
Theodore J. Perkins and Andrew G. Barto
Are Inductive Learning Algorithms Safe in a Continuous Learning Environment? / 31
Mike Barley, Michael Goebel, Hans Guesgen, and Pat Riddle
What Monkeys See and Don’t Do: Agent Models of Safe Learning in Primates / 35
Joanna J. Bryson and Marc D. Hauser
Adjustable Autonomy for the Real World / 43
Milind Tambe, Paul Scerri, and David Pynadath
Safe Adaptation in an Automotive Vehicle: The Driver Advocate / 54
Bradford W. Miller, Noel Massey, and Robert M. Gardner
Automatic Safe Learning of UML Agents / 56
Johann Schumann