Booth S, Knox WB, Shah J, Niekum S, Stone P, Allievi A. The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications. AAAI [Internet]. 2023 Jun. 26 [cited 2026 Jul. 11];37(5):5920-9. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/25733