BENDERSKY, D. A.; SANTOS, J. M. LEARNING FROM THE ENVIRONMENT WITH A UNIVERSAL REINFORCEMENT FUNCTION. International Journal of Computing, [S. l.], v. 5, n. 3, p. 68-74, 2014. DOI: 10.47839/ijc.5.3.410. Disponível em: https://computingonline.net/computing/article/view/410. Acesso em: 5 may. 2024.