Arthur Lee Samuel, (1901 - July 29, 1990 [1])
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, supervisedmove adaption to tune the evaluation of his program [2], 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 [3].
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.
Jonathan Schaeffer (1997, 2009). 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?
^ Photo and Description from Chinook - Arthur Samuel's Legacy “Arthur Samuel (standing), IBM investigator of machines that learn, watches a checker game between a human player and an electronic player - a large computer. The computer is about to win this game and type out: `Sorry, you lose.’” John Pfeiffer, The Thinking Machine, J.B. Lippincott Company, Philadelphia & NY, 1962
^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
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 [2], 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 [3].
Table of Contents
Photos
Quotes
Quote by John McCarthy from Human-Level AI is harder than it seemed in 1955 [7]:See also
Selected Publications
External Links
References
“Arthur Samuel (standing), IBM investigator of machines that learn, watches a checker game between a human player and an electronic player - a large computer. The computer is about to win this game and type out: `Sorry, you lose.’” John Pfeiffer, The Thinking Machine, J.B. Lippincott Company, Philadelphia & NY, 1962
What links here?
Up one level