Reward Redistribution as Align-RUDDER: Learning from a Few Demonstrations. International Journal of Reciprocal Symmetry and Theoretical Physics, [S. l.], v. 7, p. 1–8, 2020. Disponível em: https://ojs.bdtopten.com/3404.upright/index.php/ijrstp/article/view/52.. Acesso em: 21 sep. 2024.