Diffusion-based trajectory planners have shown strong performance in offline reinforcement learning, but their iterative denoising process often incurs high inference costs. Consistency-based planners reduce the number of sampling steps, yet they typically rely on a two-stage teacher-student distillation pipeline that increases training costs and may introduce instability. We propose Shortcut Trajectory Planning (STP), an offline model-based reinforcement learning framework that incorporates shortcut models as efficient trajectory generators. STP trains a conditional shortcut trajectory model in a single stage, supports adjustable one-step and few-step inference through step-size conditioning, and selects candidate plans using a critic augmented with feasibility-aware correction. Across standard D4RL benchmarks, including locomotion, navigation, manipulation, and dexterous control tasks, STP achieves strong performance while simplifying the training pipeline for fast generative planning.
Blogger's Review: Shortcut Trajectory Planning (STP) offers a fresh solution for offline reinforcement learning by streamlining the training process and enhancing inference efficiency. Its innovative approach effectively balances model complexity with computational efficiency, making it a noteworthy advancement, especially in complex tasks.