25,161
edits
Changes
Created page with "'''Home * People * Arthur Samuel''' FILE:This is the photo of Arthur Samuel.jpg|border|right|thumb| Arthur Samuel <ref>this photo of Arthur Samuel is earl..."
'''[[Main Page|Home]] * [[People]] * Arthur Samuel'''
[[FILE:This is the photo of Arthur Samuel.jpg|border|right|thumb| Arthur Samuel <ref>this photo of Arthur Samuel is early edition, by Xl2085, [https://en.wikipedia.org/wiki/Arthur_Samuel Arthur Samuel from Wikipedia]</ref> ]]
'''Arthur Lee Samuel''', (1901 - July 29, 1990 <ref>[https://en.wikipedia.org/wiki/Gio_Wiederhold Gio Wiederhold], [[John McCarthy]], [[Ed Feigenbaum]] ('''1990'''). ''Memorial Resolution: Arthur L. Samuel (1901 - 1990)''. [[AAAI#AIMAG|AI Magazine]], Vol. 11, No. 3</ref>)<br/>
an American computer game pioneer, who developed a [[Checkers]] program in the 50s, which appeared to be the world's first [[Learning|self-learning]] program. He already implemented a variation of [[Alpha-Beta|alpha-beta pruning]], which appeared to have been reinvented a number of times by [[John McCarthy]], [[Allen Newell]] with [[Herbert Simon]], [[Alexander Brudno]] and others. Samuel's program already used [[Bitboards|bitboards]] to [[Board Representation|represent]] the checkers board state. Arthur Samuel further was pioneer in machine learning, and first used the [[Reinforcement Learning|reinforcement learning]] technique later dubbed [[Temporal Difference Learning#TDLeaf|TDLeaf(λ)]], and, a few years later, [[Supervised Learning|supervised]] [[Automated Tuning#MoveAdaption|move adaption]] to [[Automated Tuning|tune]] the evaluation of his program <ref>[[Arthur Samuel]] ('''1967'''). ''Some Studies in Machine Learning. Using the Game of Checkers. II-Recent Progress''. [http://researcher.watson.ibm.com/researcher/files/us-beygel/samuel-checkers.pdf pdf]</ref>, where a structure of stacked linear evaluation functions was trained by computing a correlation measure based on the number of times the feature rated an alternative move higher than the desired move played by an expert <ref>[[Johannes Fürnkranz]] ('''2000'''). ''Machine Learning in Games: A Survey''. [https://en.wikipedia.org/wiki/Austrian_Research_Institute_for_Artificial_Intelligence Austrian Research Institute for Artificial Intelligence], OEFAI-TR-2000-3, [http://www.ofai.at/cgi-bin/get-tr?download=1&paper=oefai-tr-2000-31.pdf pdf]</ref>.
=Quotes=
{{Quote McCarthy on Alpha-Beta}}
=See also=
* [[Alpha-Beta]]
: [[Alpha-Beta#HistoryAlphaBeta|History of Alpha-Beta]]
* [[Bitboards]]
* [[Checkers]]
* [[History|History of Computer Chess]]
* [[Learning]]
: [[Reinforcement Learning]]
: [[Temporal Difference Learning]]
=Selected Publications=
* [[Arthur Samuel]] ('''1959'''). ''[http://domino.watson.ibm.com/tchjr/journalindex.nsf/600cc5649e2871db852568150060213c/39a870213169f45685256bfa00683d74!OpenDocument Some Studies in Machine Learning Using the Game of Checkers]''. IBM Journal July 1959, reprinted in [[David Levy]] (ed.) ('''1988'''). ''[http://link.springer.com/book/10.1007/978-1-4613-8716-9 Computer Games I]''. <ref>[http://www.abaa.org/books/245839575.html Some studies in machine learning using the game of checkers by Arthur Lee Samuel from Jeremy Norman's Historyofscience.com - Used Book - Paperback - First Edition]</ref> <ref>[[Norbert Wiener]] ('''1964'''). ''God & Golem, Inc''.: A Comment on Certain Points Where Cybernetics Impinges on Religion - MIT Press, Cambridge, MA - [http://luisguillermo.com/diosygolem/God_and_Golem_Inc.pdf pdf], refers Samuel's Checkers at pp. 11</ref>
* [[Arthur Samuel]] ('''1960'''). ''[http://www.sciencedirect.com/science/article/pii/S0065245808606087 Programming Computers to Play Games]''. [http://www.sciencedirect.com/science/bookseries/00652458/1 Advances in Computers, Vol. 1], pp. 165-192
* [[Arthur Samuel]] ('''1967'''). ''Some Studies in Machine Learning. Using the Game of Checkers. II-Recent Progress''. [http://researcher.watson.ibm.com/researcher/files/us-beygel/samuel-checkers.pdf pdf]
* [[Hans Berliner]], [[Richard Greenblatt]], [[Jacques Pitrat]], [[Arthur Samuel]], [[David Slate]] ('''1977'''). ''Panel on Computer Game Playing''. [[Conferences#IJCAI1977|IJCAI 1977]], [http://ijcai.org/Past%20Proceedings/IJCAI-77-VOL2/PDF/087.pdf pdf]
* [https://en.wikipedia.org/wiki/Gio_Wiederhold Gio Wiederhold], [[John McCarthy]], [[Edward Feigenbaum]] ('''1990'''). ''Memorial Resolution: Arthur L. Samuel (1901 - 1990)''. [[AAAI#AIMAG|AI Magazine]], Vol. 11, No. 3
* [[John McCarthy]], [[Edward Feigenbaum]] ('''1991'''). ''In Memoriam. Arthur L. Samuel: Pioneer in Machine Learning.'' [[ICGA Journal#14_1|ICCA Journal, Vol. 14, No. 1]]
* [[Jonathan Schaeffer]] ('''1997, 2009'''). ''[http://www.springer.com/computer/artificial/book/978-0-387-76575-4 One Jump Ahead] Challenging Human Supremacy in Checkers'', Springer, ISBN 0-387-94930-5, ISBN 978-0-387-76575-4, Didn't Samuel Solve That Game?
=External Links=
* [https://en.wikipedia.org/wiki/Arthur_Samuel Arthur Samuel from Wikipedia]
* [http://infolab.stanford.edu/pub/voy/museum/samuel.html Arthur Samuel: Pioneer in Machine Learning] by [[John McCarthy]] from [http://infolab.stanford.edu/pub/voy/museum.html Stanford Computer History Exhibits]
* [http://www.computer.org/portal/web/awards/cp-samuel Arthur L. Samuel | 1987 Computer Pioneer Award] from [[IEEE#Awards|IEEE Computer Society Awards]]
* [http://www-formal.stanford.edu/jmc/slides/wrong/wrong-sli/wrong-sli.html Human-Level AI is harder than it seemed in 1955] by [[John McCarthy]]
* [https://webdocs.cs.ualberta.ca/~jonathan/publications/ai_publications/samuel.pdf Samuel's Checkers Player] (pdf) from ''Reinforcement Learning'' by [[Richard Sutton]] and [[Andrew Barto]] <ref>[[Richard Sutton]], [[Andrew Barto]] ('''1998'''). ''Reinforcement Learning: An Introduction''. [https://en.wikipedia.org/wiki/MIT_Press MIT Press], Cambridge, Mass. ISBN 0-2621-9398-1.</ref>
* [http://www.cs.ualberta.ca/~chinook/project/legacy.html Chinook - Arthur Samuel's Legacy]
=References=
<references />
'''[[People|Up one level]]'''
[[FILE:This is the photo of Arthur Samuel.jpg|border|right|thumb| Arthur Samuel <ref>this photo of Arthur Samuel is early edition, by Xl2085, [https://en.wikipedia.org/wiki/Arthur_Samuel Arthur Samuel from Wikipedia]</ref> ]]
'''Arthur Lee Samuel''', (1901 - July 29, 1990 <ref>[https://en.wikipedia.org/wiki/Gio_Wiederhold Gio Wiederhold], [[John McCarthy]], [[Ed Feigenbaum]] ('''1990'''). ''Memorial Resolution: Arthur L. Samuel (1901 - 1990)''. [[AAAI#AIMAG|AI Magazine]], Vol. 11, No. 3</ref>)<br/>
an American computer game pioneer, who developed a [[Checkers]] program in the 50s, which appeared to be the world's first [[Learning|self-learning]] program. He already implemented a variation of [[Alpha-Beta|alpha-beta pruning]], which appeared to have been reinvented a number of times by [[John McCarthy]], [[Allen Newell]] with [[Herbert Simon]], [[Alexander Brudno]] and others. Samuel's program already used [[Bitboards|bitboards]] to [[Board Representation|represent]] the checkers board state. Arthur Samuel further was pioneer in machine learning, and first used the [[Reinforcement Learning|reinforcement learning]] technique later dubbed [[Temporal Difference Learning#TDLeaf|TDLeaf(λ)]], and, a few years later, [[Supervised Learning|supervised]] [[Automated Tuning#MoveAdaption|move adaption]] to [[Automated Tuning|tune]] the evaluation of his program <ref>[[Arthur Samuel]] ('''1967'''). ''Some Studies in Machine Learning. Using the Game of Checkers. II-Recent Progress''. [http://researcher.watson.ibm.com/researcher/files/us-beygel/samuel-checkers.pdf pdf]</ref>, where a structure of stacked linear evaluation functions was trained by computing a correlation measure based on the number of times the feature rated an alternative move higher than the desired move played by an expert <ref>[[Johannes Fürnkranz]] ('''2000'''). ''Machine Learning in Games: A Survey''. [https://en.wikipedia.org/wiki/Austrian_Research_Institute_for_Artificial_Intelligence Austrian Research Institute for Artificial Intelligence], OEFAI-TR-2000-3, [http://www.ofai.at/cgi-bin/get-tr?download=1&paper=oefai-tr-2000-31.pdf pdf]</ref>.
=Quotes=
{{Quote McCarthy on Alpha-Beta}}
=See also=
* [[Alpha-Beta]]
: [[Alpha-Beta#HistoryAlphaBeta|History of Alpha-Beta]]
* [[Bitboards]]
* [[Checkers]]
* [[History|History of Computer Chess]]
* [[Learning]]
: [[Reinforcement Learning]]
: [[Temporal Difference Learning]]
=Selected Publications=
* [[Arthur Samuel]] ('''1959'''). ''[http://domino.watson.ibm.com/tchjr/journalindex.nsf/600cc5649e2871db852568150060213c/39a870213169f45685256bfa00683d74!OpenDocument Some Studies in Machine Learning Using the Game of Checkers]''. IBM Journal July 1959, reprinted in [[David Levy]] (ed.) ('''1988'''). ''[http://link.springer.com/book/10.1007/978-1-4613-8716-9 Computer Games I]''. <ref>[http://www.abaa.org/books/245839575.html Some studies in machine learning using the game of checkers by Arthur Lee Samuel from Jeremy Norman's Historyofscience.com - Used Book - Paperback - First Edition]</ref> <ref>[[Norbert Wiener]] ('''1964'''). ''God & Golem, Inc''.: A Comment on Certain Points Where Cybernetics Impinges on Religion - MIT Press, Cambridge, MA - [http://luisguillermo.com/diosygolem/God_and_Golem_Inc.pdf pdf], refers Samuel's Checkers at pp. 11</ref>
* [[Arthur Samuel]] ('''1960'''). ''[http://www.sciencedirect.com/science/article/pii/S0065245808606087 Programming Computers to Play Games]''. [http://www.sciencedirect.com/science/bookseries/00652458/1 Advances in Computers, Vol. 1], pp. 165-192
* [[Arthur Samuel]] ('''1967'''). ''Some Studies in Machine Learning. Using the Game of Checkers. II-Recent Progress''. [http://researcher.watson.ibm.com/researcher/files/us-beygel/samuel-checkers.pdf pdf]
* [[Hans Berliner]], [[Richard Greenblatt]], [[Jacques Pitrat]], [[Arthur Samuel]], [[David Slate]] ('''1977'''). ''Panel on Computer Game Playing''. [[Conferences#IJCAI1977|IJCAI 1977]], [http://ijcai.org/Past%20Proceedings/IJCAI-77-VOL2/PDF/087.pdf pdf]
* [https://en.wikipedia.org/wiki/Gio_Wiederhold Gio Wiederhold], [[John McCarthy]], [[Edward Feigenbaum]] ('''1990'''). ''Memorial Resolution: Arthur L. Samuel (1901 - 1990)''. [[AAAI#AIMAG|AI Magazine]], Vol. 11, No. 3
* [[John McCarthy]], [[Edward Feigenbaum]] ('''1991'''). ''In Memoriam. Arthur L. Samuel: Pioneer in Machine Learning.'' [[ICGA Journal#14_1|ICCA Journal, Vol. 14, No. 1]]
* [[Jonathan Schaeffer]] ('''1997, 2009'''). ''[http://www.springer.com/computer/artificial/book/978-0-387-76575-4 One Jump Ahead] Challenging Human Supremacy in Checkers'', Springer, ISBN 0-387-94930-5, ISBN 978-0-387-76575-4, Didn't Samuel Solve That Game?
=External Links=
* [https://en.wikipedia.org/wiki/Arthur_Samuel Arthur Samuel from Wikipedia]
* [http://infolab.stanford.edu/pub/voy/museum/samuel.html Arthur Samuel: Pioneer in Machine Learning] by [[John McCarthy]] from [http://infolab.stanford.edu/pub/voy/museum.html Stanford Computer History Exhibits]
* [http://www.computer.org/portal/web/awards/cp-samuel Arthur L. Samuel | 1987 Computer Pioneer Award] from [[IEEE#Awards|IEEE Computer Society Awards]]
* [http://www-formal.stanford.edu/jmc/slides/wrong/wrong-sli/wrong-sli.html Human-Level AI is harder than it seemed in 1955] by [[John McCarthy]]
* [https://webdocs.cs.ualberta.ca/~jonathan/publications/ai_publications/samuel.pdf Samuel's Checkers Player] (pdf) from ''Reinforcement Learning'' by [[Richard Sutton]] and [[Andrew Barto]] <ref>[[Richard Sutton]], [[Andrew Barto]] ('''1998'''). ''Reinforcement Learning: An Introduction''. [https://en.wikipedia.org/wiki/MIT_Press MIT Press], Cambridge, Mass. ISBN 0-2621-9398-1.</ref>
* [http://www.cs.ualberta.ca/~chinook/project/legacy.html Chinook - Arthur Samuel's Legacy]
=References=
<references />
'''[[People|Up one level]]'''
