Tech-Report Announcement

[white@cs.rochester.edu]

The following technical report is now available:

		
		LEARNING TO PERCEIVE AND ACT
		
	   Steven D. Whitehead and Dana H. Ballard
	
		Technical Report # 331 (Revised)
		 Department of Computer Science	
		    University of Rochester
		      Rochester, NY 14627

ABSTRACT:  This paper considers adaptive control architectures that
integrate active sensory-motor systems with decision systems based 
on reinforcement learning. One unavoidable consequence of active perception 
is that the agent's internal representation often confounds external world 
states.  We call this phenomenon perceptual aliasing and show that it 
destabilizes existing reinforcement learning algorithms with respect 
to the optimal decision policy.  We then describe a new decision system 
that overcomes these difficulties for a restricted class of decision 
problems.  The system incorporates a perceptual subcycle within the overall 
decision cycle and uses a modified learning algorithm to suppress the effects 
of perceptual aliasing. The result is a control architecture that learns not 
only how to solve a task but also where to focus its attention in order to 
collect necessary sensory information.


The report can be obtained by sending requests to either peg at cs.rochester.edu 
or white at cs.rochester.edu.  Be sure to mention TR331(revised) in your request.