Dates:    29-Jan-97
Time:     3:00 PM
Cboards:  general 5409
Place:    WeH 5409
Type:     Thesis Proposal
Who:      Peter Stone
Topic:    Layered Learning in Multiagent Systems

			ABSTRACT


   Multiagent  Systems  is  the emerging subfield of Artificial Intelligence
   that aims to provide both principles for construction of complex  systems
   involving  multiple agents and mechanisms for coordination of independent
   agents' behaviors.  As of yet, there has been little work with Multiagent
   Systems that require real-time control in noisy environments.  Because of
   the inherent complexity  of  this  type  of  Multiagent  System,  Machine
   Learning  is  an  interesting and promising area to merge with Multiagent
   Systems.  Machine learning has the potential to provide robust mechanisms
   that  leverage  upon  experience to equip agents with a large spectrum of
   behaviors, ranging from effective individual performance in  a  team,  to
   collaborative  achievement  of  independently  and jointly set high-level
   goals in the presence of adversaries.  Learning  will  also  help  agents
   adapt  to  unforeseen behaviors on the parts of other agents, through the
   use of on-line  adaptive  methods  that  may  include  explicit  opponent
   modelling.    This  thesis  will  focus  on learning in this particularly
   complex class of multiagent  domains.    The  principal  question  to  be
   answered  is  Can  agents  learn  to  work together in a real-time, noisy
   environment in the presence of both teammates and adversaries?  I propose
   to  design  and  develop  a  multiagent learning system in the context of
   robotic soccer as  an  example  of  one  such  domain.    Based  on  this
   challenging  case  study,  I expect to introduce a new general multiagent
   learning method, Layered Learning, by which similar systems can be  built
   in  any  such domain.  Layered Learning allows for a bottom-up definition
   of agent capabilities  at  different  levels  in  a  complete  multiagent
   domain.    Machine Learning opportunities are identified when hand-coding
   solutions are too  complex  to  generate.  Individual  and  collaborative
   behaviors  in  the  presence  of  adversaries are organized, learned, and
   combined in a layered fashion. I will demonstrate  the  effectiveness  of
   Layered Learning in the robotic soccer domain.