@COMMENT This file was generated by bib2html.pl version 0.915
@COMMENT written by Patrick Riley
@COMMENT This file came from Patrick Riley's publication pages at
@COMMENT http://www.cs.cmu.edu/~pfr/publications
@PhdThesis{riley05:thesis,
author = {Patrick Riley},
title = {Coaching: Learning and Using Environment and Agent
Models for Advice},
school = {Computer Science Dept., Carnegie Mellon University},
year = 2005,
note = {CMU-CS-05-100},
bib2html_dl_pdf = {http://www.cs.cmu.edu/~pfr/thesis/pfr_thesis.pdf},
bib2html_dl_psgz = {http://www.cs.cmu.edu/~pfr/thesis/pfr_thesis.ps.gz},
abstract = {Coaching is a relationship where one agent provides
advice to another about how to act. This thesis
explores a range of problems faced by an automated
coach agent in providing advice to one or more
automated advice-receiving agents. The coach's job
is to help the agents perform as well as possible in
their environment. We identify and address a set of
technical challenges: How can the coach learn and
use models of the environment? How should advice be
adapted to the peculiarities of the advice
receivers? How can opponents be modeled, and how can
those models be used? How should advice be
represented to be effectively used by a team? This
thesis serves both to define the coaching problem
and explore solutions to the challenges posed. This
thesis is inspired by a simulated robot soccer
environment with a coach agent who can provide
advice to a team in a standard language. This author
developed, in collaboration with others, this coach
environment and standard language as the thesis
progressed. The experiments in this thesis represent
the largest known empirical study in the simulated
robot soccer environment. A predator-prey domain and
and a moving maze environment are used for
additional experimentation. All algorithms are
implemented in at least one of these environments
and empirical validation is performed. In addition
to the coach problem formulation and decompositions,
the thesis makes several main technical
contributions: (i) Several opponent model
representations with associated learning algorithms,
whose effectiveness in the robot soccer domain is
demonstrated. (ii) A study of the effects and need
for coach learning under various limitations of the
advice receiver and communication bandwidth. (iii)
The Multi-Agent Simple Temporal Network, a
multi-agent plan representation which is refinement
of a Simple Temporal Network, with an associated
distributed plan execution algorithm. (iv)
Algorithms for learning an abstract Markov Decision
Process from external observations, a given state
abstraction, and partial abstract action
templates. The use of the learned MDP for advice is
explored in various scenarios. }
}