papers on hybrid reinforcement learning

[rsun@cecs.missouri.edu]

Two papers on hybrid reinforcement learning:
combining symbolic and neural methods for reinforcement learning

accessible from  http://www.cecs.missouri.edu/~rsun/hybrid-rl.html



----------------------------------------------------------------------------


Supplementing Neural Reinforcement Learning with Symbolic Methods

Ron Sun

Several different ways of using symbolic methods to enhance reinforcement 
learning are identified and discussed in some detail.
Each demonstrates to some extent the potential advantages of
combining RL and symbolic methods.  Different from existing work, in 
combining RL and symbolic methods, we focus on autonomous learning
from scratch without a priori domain-specific knowledge.
Thus the role of symbolic methods lies truly in enhancing learning,
not in providing a priori domain-specific knowledge.
These discussed methods point to the possibilities and the challenges
in this line of research.



----------------------------------------------------------------------------

Beyond Simple Rule Extraction: Acquiring Planning Knowledge from Neural Networks

Ron Sun
Todd Peterson
Chad Sessions

This paper discusses learning in hybrid models that goes
beyond simple classification rule extraction from backpropagation networks.
Although simple rule extraction has received a lot of research
attention, we need to further develop hybrid learning models that
learn autonomously and acquire both symbolic and subsymbolic knowledge.
It is also necessary to study  autonomous learning of both subsymbolic
and symbolic knowledge in integrated architectures.
This paper will describe planning knowledge extraction from
neural reinforcement learning that goes beyond extracting simple rules.
It includes two approaches towards extracting  planning  knowledge:
the extraction of symbolic rules from neural reinforcement
learning,  and the extraction of complete plans.  This work points to 
a general framework for achieving the subsymbolic to  symbolic 
transition in an integrated autonomous learning framework.





-------------------------------------------------------------------------
Both papers are
accessible from  http://www.cecs.missouri.edu/~rsun/hybrid-rl.html




===========================================================================
Prof. Ron Sun                           http://www.cecs.missouri.edu/~rsun
CECS Department                         phone: (573) 884-7662
University of Missouri-Columbia         fax:   (573) 882 8318 
201 Engineering Building West
Columbia, MO 65211-2060                 email: rsun at cecs.missouri.edu 

http://www.cecs.missouri.edu/~rsun
http://www.cecs.missouri.edu/~rsun/journal.html
http://www.elsevier.com/locate/cogsys
===========================================================================