DiDrive: A Risk-Aware Hierarchical Diffusion Framework for Safe Offline Reinforcement Learning in Autonomous Driving
DiDrive, a distribution-guided offline diffusion framework featuring two synergistic components: the Risk-Aware Hierarchical Diffusion (RHDif) architecture and the 3DICE policy optimization paradigm, is proposed, providing a robust pathway for safe autonomous driving decision-making.
Qi-Song Guo, Jing-Tang Chen, Zhi-Lin Chen et al.
· 0 citations