A learning algorithm for the finite-time two-armed bandit problem

Mitsuo Sato, Kenichi Abe, Hiroshi Takeda. A learning algorithm for the finite-time two-armed bandit problem. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 14(3):528-534, 1984. [doi]

Authors

Mitsuo Sato

This author has not been identified. Look up 'Mitsuo Sato' in Google

Kenichi Abe

This author has not been identified. Look up 'Kenichi Abe' in Google

Hiroshi Takeda

This author has not been identified. Look up 'Hiroshi Takeda' in Google