Bozinovski, S. «[Q-learning, p. 320-325, a Google Books Crossbar Adaptive Array: The first connectionist network that solved the delayed reinforcement learning problem]». A: Dobnikar. Artificial Neural Nets and Genetic Algorithms: Proceedings of the International Conference in Portorož, Slovenia, 1999 (en anglès). Springer Science & Business Media, 15 juliol 1999, p. 320–325. ISBN 978-3-211-83364-3.
Bozinovski, S. «[Q-learning, p. 397, a Google Books A self learning system using secondary reinforcement]». A: Trappl. Cybernetics and Systems Research: Proceedings of the Sixth European Meeting on Cybernetics and Systems Research (en anglès). North Holland, 1982, p. 397–402. ISBN 978-0-444-86488-8.
