Modular Networks for Reinforcement Learning of Backgammon Strategies

[Justin Boyan]

The file  boyan.backgammon-thesis.ps.Z  is now available in the
neuroprose archive.
_______________________

  Modular Neural Networks for Learning Context-Dependent Game Strategies

			   Justin A. Boyan
	       Master's Thesis, University of Cambridge,
	       Computer Speech and Language Processing

		Supervisor:  Professor Frank Fallside
			    17 August 1992

  Abstract:

     Recent results by Tesauro in the domain of backgammon indicate that
  a  neural network, trained  by temporal difference methods to evaluate
  positions   generated by self-play,  can reach  an   advanced level of
  backgammon skill.  For my  summer thesis  project, I first implemented
  the  TD/neural  network learning  algorithms  and  confirmed Tesauro's
  results,   using the domains   of  tic-tac-toe and  backgammon.  Then,
  motivated by Waibel's success with modular neural networks for phoneme
  recognition, I experimented with using  two modular architectures (DDD
  and Meta-Pi) in place of the monolithic  networks.  I found that using
  the   modular networks significantly   enhanced  the ability   of  the
  backgammon evaluator to change  its  strategic priorities depending on
  the  current game context.   My   best modular backgammon network  was
  entered  in the  1992 Computer  Games  Olympiad in   London, where  it
  finished in second place.


_______________________

Here is an example of how to retrieve this paper:

> ftp archive.cis.ohio-state.edu        (or ftp 128.146.8.52)
Connected to archive.cis.ohio-state.edu.
220 archive.cis.ohio-state.edu FTP server ready.
Name: anonymous
331 Guest login ok, send ident as password.
Password:<type your email address here>
230 Guest login ok, access restrictions apply.
ftp> binary
200 Type set to I.
ftp> cd pub/neuroprose
250 CWD command successful.
ftp> get boyan.backgammon-thesis.ps.Z
200 PORT command successful.
150 Opening BINARY mode data connection for boyan.backgammon-thesis.ps.Z
226 Transfer complete.
ftp> quit
221 Goodbye.
> uncompress boyan.backgammon-thesis.ps.Z
> lpr boyan.backgammon-thesis.ps