Orego

 
 
Orego is a multi-year project to develop programs to play the classical Asian game of Go.


Code and documentation are available. Orego is currently distributed under the GNU General Public License.


People

Dr. Peter Drake, Associate Professor of Computer Science, Lewis & Clark College


Dr. Yung-Pin Chen, Associate Professor of Statistics, Lewis & Clark College


Dr. Jens Mache, Associate Professor of Computer Science, Lewis & Clark College


Jason Galbraith, Robotics and Programming Instructor, Sunset High School, Beaverton, OR


Bobby Dygert (University of Buffalo ‘11)

Walt Javins (Lewis & Clark ‘11)

Travis Mandel (Carnegie Mellon University ‘11)

Jessica Mullins (Lewis & Clark ‘10)

Seth Pellegrino (Lewis & Clark ‘10)

Drew Tillis (Hendrix College ‘10)


Previous team members include Heather Cook (Lewis & Clark '03), Jason Galbraith (Robotics and Programming Instructor, Sunset High School, Beaverton, Oregon), Andrew Hubbard (University of Maryland, Baltimore County ’09), Kevin Imber (Lewis & Clark ’09), Dr. Jim Levenick (Associate Professor of Computer Science, Willamette University), Seth Pellegrino (Lewis & Clark ’09), Andrew Pouliot (Lewis & Clark ‘09), Niku Schreiner (Lewis & Clark '07), John Stogin (Princeton ’11), Brett Tomlin (Lewis & Clark '05), Bjorn Vanberg (Lewis & Clark '07), Loring Veenstra (Lewis & Clark '06), Amanda Venghaus (Lewis & Clark '04), and Steve Uurtamo (working on a PhD at SUNY Buffalo).


Acknowledgments

The Orego project has been aided by grants from the Atkinson Faculty Development Program (Willamette University), the W. M. Keck Foundation, and the John S. Rogers Science Research Program (Lewis & Clark College). Since 2008, Orego has been part of the Willamette Valley REU-RET Consortium for Mathematics Research, funded by the National Science Foundation.


Publications and Presentations

Drake, P. (2009). “Computer Go”. Presentation at SuperQuest-CS4HS, Monmouth, Oregon.


Dygert, R., Mandel, T., Mache, J., and Drake, P. (2009). “Root and leaf parallelization: Adapting Monte-Carlo tree search for a cluster”. Poster presented at the 2009 poster conference of the Willamette Valley REU-RET Consortium for Mathematics Research at the University of Portland.


Galbraith, J., Pellegrino, S., and Drake, P. (2009). “Localized Search Using Covariance”. Poster presented at the 2009 poster conference of the Willamette Valley REU-RET Consortium for Mathematics Research at the University of Portland.


Javins, W., Chen, Y.-P., and Drake, P. (2009). “Computer Go: Enhancing Monte-Carlo Tree Search with RAVE”. Poster presented at the 2009 poster conference of the Willamette Valley REU-RET Consortium for Mathematics Research at the University of Portland and at the 2009 John Rogers Summer Research Conference at Lewis & Clark College.


Mullins, J., Tillis, D., and Drake, P. (2009). “Implementing an opening book in computer Go”. Poster presented at the 2009 poster conference of the Willamette Valley REU-RET Consortium for Mathematics Research at the University of Portland and at the 2009 John Rogers Summer Research Conference at Lewis & Clark College.


Stogin, J., Chen, Y.-P., Drake, P., and Pellegrino, S. (2009) “The Beta Distribution in the UCB Algorithm Applied to Monte-Carlo Go”. In Proceedings of the 2009 International Conference on Artificial Intelligence, CSREA Press.


Drake, P. & Chen, Y.-P. (2008) “Coevolving Partial Strategies for the Game of Go”. In Proceedings of the 2008 International Conference on Genetic and Evolutionary Methods, CSREA Press.


Drake, P., and Uurtamo, S. (2007). “Move Ordering vs Heavy Playouts: Where Should Heuristics Be Applied in Monte Carlo Go?”. In Proceedings of the 3rd North American Game-On Conference.


Drake, P., and Uurtamo, S. (2007). “Heuristics in Monte Carlo Go”. In Proceedings of the 2007 International Conference on Artificial Intelligence, CSREA Press.


Drake, P. (2006). “A Simple Architecture For Small-Board Computer Go”. Abstract published in K. Doxsee (Ed.) (2006), Proceedings of the Oregon Academy of Science, Volume XLII.


Drake, P., Schreiner, N., Tomlin, B., & Veenstra, L. (2006). “An Efficient Algorithm for Eyespace Classification in Go”. In Proceedings of the 2006 International Conference on Artificial Intelligence, CSREA Press.


Schreiner, N., Vanberg, B., Pouliot, A., & Drake, P. (2006). “Solving Tactical Go Problems Using Monte Carlo Search”. Poster presented at the 2006 John Rogers Summer Research Conference at Lewis & Clark College and the Thirteenth Regional Conference on Undergraduate Research, Murdock College Research Program at the University of Portland.


Schreiner, N., Tomlin, B., Veenstra, L., & Drake, P. (2005). “A Blackboard Architecture for Computer Go”. Poster presented at the 2005 John Rogers Summer Research Conference at Lewis & Clark College.


Veenstra, L., Venghaus, A., & Drake, P. (2004). “Pattern Matching in the Game of Go”. Poster presented at the 2004 John Rogers Summer Research Conference at Lewis & Clark College and the Thirteenth Regional Conference on Undergraduate Research, Murdock College Research Program at Lewis & Clark College.


Cook, H., Venghaus, A., & Drake, P. (2003). “Machine Learning Applied to the Game of Go”. Abstract published in B. Gilbert (Ed.) (2004), Proceedings of the Oregon Academy of Science, Volume XL. Poster presented at the 2003 John Rogers Summer Research Conference at Lewis & Clark College, at the Twelfth Regional Conference on Undergraduate Research, Murdock College Research Program at Pacific Lutheran University, and at the 2004 meeting of the Oregon Academy of Sciences at Portland State University.


Resources

Go

American Go Association, including an introduction to the game

GoBase, including a section on computer Go

Sensei's Library

goproblems.com

KGS Go Server

Oregon Go


Computer Go

Computer Go Mailing List

CiteULike - Computer Go

Computer Go Tournaments on KGS

Go Text Protocol (GTP)

Smart Game Format (SGF)


Training & Testing Data

Computer Go Test Collection

Kogo's Joseki Dictionary

Game Records:

  1. British Go Association

  2. Scored, 9x9 games collected by Nici Schraudolph, in his condensed one-line format

Problem Collections:

  1. Professional games in Smart Go Format