Checkers Player       

Artificial Intelligence Accomplishment | 1959

IBM researcher: Arthur Lee Samuel

Where the work was done: IBM Poughkeepsie Laboratory

What we accomplished: Samuel (pictured) made the first checkers program to demonstrate that computers can learn from experience. In 1961 he put his program up against the Connecticut state checker champion, the number four ranked player in the nation. His checkers program won. Samuel went on to use techniques such as mutable evaluation functions, hill climbing, and signature tables to explore rote and generalization learning. His work greatly influenced the instruction set of early IBM computers.

Related links: Wikipedia Article; Some Studies in Machine Learning Using the Game of Checkers (IEEE sign-in); The Origins of Artificial Intelligence Computing; What is Artificial Intelligence; A Brief History of Computer Checkers

 

BACK TO ARTIFICIAL INTELLIGENCE

BACK TO IBM RESEARCH ACCOMPLISHMENTS