He, Zhouyu, Peng Qiao, Rongchun Li, Yong Dou, and Yusong Tan. 2025. “Highly Parallelized Reinforcement Learning Training With Relaxed Assignment Dependencies”. Proceedings of the AAAI Conference on Artificial Intelligence 39 (16):17159-67. https://doi.org/10.1609/aaai.v39i16.33886.