Offline Reinforcement Learning with Generative Trajectory Policies 文章

ArXiv CS.AI2026-05-29NEWSen作者: Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen

查看原文 →

Offline Reinforcement Learning with Generative Trajectory Policies · 相关技术

相关技术

ordinary differential equation (ODE)Consistency models Flow Matching Diffusion Consistency Policies Diffusion Policies reinforcement learning