Offline Meta-Reinforcement Learning for Cold-Start Adaptation in Multi-Cloud Auto-Scaling, Addressing Data Scarcity and Action-Space Explosion in CARL Frameworks. The Science Post, [S. l.], v. 2, n. 3, 2026. Disponível em: https://www.thesciencepostjournal.com/index.php/tsp/article/view/329. Acesso em: 29 sep. 2026.