SAMBO-RL: Shifts-aware Model-based Offline Reinforcement Learning.

Wang Luo Haoran Li 0027 Zicheng Zhang Congying Han Jiayu Lv Tiande Guo SAMBO-RL: Shifts-aware Model-based Offline Reinforcement Learning. 2024 abs/2408.12830 CoRR https://doi.org/10.48550/arXiv.2408.12830 db/journals/corr/corr2408.html#abs-2408-12830 streams/journals/corr