Difference between revisions of "Arthur Samuel"

From Chessprogramming wiki
Jump to: navigation, search
Line 39: Line 39:
 
* [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>
 
* [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]
 
* [http://www.cs.ualberta.ca/~chinook/project/legacy.html Chinook - Arthur Samuel's Legacy]
 +
* [https://en.chessbase.com/post/standing-on-the-shoulders-of-giants Standing on the shoulders of giants] by [[Albert Silver]], [[ChessBase|ChessBase News]], September 18, 2019
  
 
=References=  
 
=References=  

Revision as of 21:20, 24 September 2019

Home * People * Arthur Samuel

Arthur Lee Samuel, (1901 - July 29, 1990 [2])
was an American computer game pioneer, who developed a Checkers program in the 50s, which appeared to be the world's first self-learning program. He already implemented a variation of 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 to represent the checkers board state. Arthur Samuel further was pioneer in machine learning, and first used the reinforcement learning technique later dubbed TDLeaf(λ), and, a few years later, supervised move adaption to tune the evaluation of his program [3], 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 [4].

Quotes

Quote by John McCarthy from Human-Level AI is harder than it seemed in 1955 on the Dartmouth workshop:

Chess programs catch some of the human chess playing abilities but rely on the limited effective branching of the chess move tree. The ideas that work for chess are inadequate for go. Alpha-beta pruning characterizes human play, but it wasn't noticed by early chess programmers - Turing, Shannon, Pasta and Ulam, and Bernstein. We humans are not very good at identifying the heuristics we ourselves use. Approximations to alpha-beta used by Samuel, Newell and Simon, McCarthy. Proved equivalent to minimax by Hart and Levin, independently by Brudno. Knuth gives details.

See also

History of Alpha-Beta
Reinforcement Learning
Temporal Difference Learning

Selected Publications

1959

1960 ...

1980 ....

2000 ...

External Links

References

  1. this photo of Arthur Samuel is early edition, by Xl2085, Arthur Samuel from Wikipedia
  2. Gio Wiederhold, John McCarthy, Ed Feigenbaum (1990). Memorial Resolution: Arthur L. Samuel (1901 - 1990). AI Magazine, Vol. 11, No. 3
  3. Arthur Samuel (1967). Some Studies in Machine Learning. Using the Game of Checkers. II-Recent Progress. pdf
  4. Johannes Fürnkranz (2000). Machine Learning in Games: A Survey. Austrian Research Institute for Artificial Intelligence, OEFAI-TR-2000-3, pdf
  5. 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
  6. Norbert Wiener (1964). God & Golem, Inc.: A Comment on Certain Points Where Cybernetics Impinges on Religion - MIT Press, Cambridge, MA - pdf, refers Samuel's Checkers at pp. 11
  7. Richard Sutton, Andrew Barto (1998). Reinforcement Learning: An Introduction. MIT Press, Cambridge, Mass. ISBN 0-2621-9398-1.

Up one level