Combining Reinforcement Learning and Human Feedback for AI System Optimization. International Journal of Supportive Research, ISSN: 3079-4692, [S. l.], v. 2, n. 1, p. 31–39, 2024. Disponível em: https://ijsupport.com/index.php/ijsrs/article/view/12. Acesso em: 23 jul. 2025.