Lin, Haoxin, Hongqiu Wu, Jiaji Zhang, Yihao Sun, Junyin Ye, and Yang Yu. 2024. “Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward”. Proceedings of the AAAI Conference on Artificial Intelligence 38 (12):13808-16. https://doi.org/10.1609/aaai.v38i12.29287.