[1] H. Robbins:
A sequential decision problem with a finite memory. Proc. Nat. Acad. Sci. 42 (1956), 920-923.
MR 0082762 |
Zbl 0073.13402
[3] C. V. Smith R. Pyke:
The Robbins-lsbell two-armed-bandit problem with finite memory. Ann. Math. Statist. 36 (1965), 1375-1386.
MR 0182107
[4] W. Feller:
An Introduction to Probability Theory and its Applications. Vol. 1 (2. vyd.). J. Wiley, New York 1957.
MR 0088081 |
Zbl 0077.12201