OBADAN, S.; WANG, Z. A MULTI-AGENT APPROACH TO POMDPS USING OFF-POLICY REINFORCEMENT LEARNING AND GENETIC ALGORITHMS. International Journal of Computing, [S. l.], v. 19, n. 3, p. 377-386, 2020. DOI: 10.47839/ijc.19.3.1887. Disponível em: https://computingonline.net/computing/article/view/1887. Acesso em: 22 dec. 2024.