Diffusion reward: Learning rewards via conditional video diffusion

作者：Tao Huang, Guangqi Jiang, Yanjie Ze, Huazhe Xu · 单位：Shanghai Qi Zhi Institute The Chinese University of Hong Kong Sichuan University Tsinghua University, IIIS Shanghai AI Laboratory, Shanghai Qi Zhi Institute The Chinese University of Hong Kong Sichuan University Tsinghua University, IIIS Shanghai AI Laboratory diffus · 会议/期刊：ECCV 2024 · 方向：扩散特性利用 · 发布日期：2024