Efficient Diffusion Planning with Temporal Diffusion
Jiaming Guo, Rui Zhang, Zerun Li, Yunkai Gao, Shaohui Peng, Siming Lan, Xing Hu, Zidong Du, Xishan Zhang, Ling Li

TL;DR
The paper introduces Temporal Diffusion Planner (TDP), a method that improves decision efficiency in diffusion planning by updating plans incrementally over time, reducing computational costs and maintaining high performance.
Contribution
TDP distributes denoising steps across time, enabling efficient plan updates and incorporating automated replanning to align plans with reality.
Findings
TDP increases decision frequency by 11-24.8 times.
TDP achieves higher or comparable performance to previous methods.
TDP reduces computational overhead in diffusion planning.
Abstract
Diffusion planning is a promising method for learning high-performance policies from offline data. To avoid the impact of discrepancies between planning and reality on performance, previous works generate new plans at each time step. However, this incurs significant computational overhead and leads to lower decision frequencies, and frequent plan switching may also affect performance. In contrast, humans might create detailed short-term plans and more general, sometimes vague, long-term plans, and adjust them over time. Inspired by this, we propose the Temporal Diffusion Planner (TDP) which improves decision efficiency by distributing the denoising steps across the time dimension. TDP begins by generating an initial plan that becomes progressively more vague over time. At each subsequent time step, rather than generating an entirely new plan, TDP updates the previous one with a small…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsAI-based Problem Solving and Planning · Reinforcement Learning in Robotics · Artificial Intelligence in Games
