mlsanityData to 14 Oct 2026

Mixed-Density Diffuser: Efficient Planning with Non-Uniform Temporal Resolution

arXiv 2510.23026 ↗First posted 27 Oct 2025cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent studies demonstrate that diffusion planners benefit from sparse-step planning over single-step planning. Training models to skip steps in their trajectories helps capture long-term dependencies without additional memory or computational cost. However, predicting excessively sparse plans degrades performance. We hypothesize this temporal density threshold is non-uniform across a planning horizon and that certain parts of a predicted trajectory should be more densely generated. We propose Mixed-Density Diffuser (MDD), a diffusion planner where the densities throughout the horizon are tunable hyperparameters. We show that MDD surpasses the SOTA Diffusion Veteran (DV) framework across the Maze2D, Franka Kitchen, and Antmaze Datasets for Deep Data-Driven Reinforcement Learning (D4RL) task domains, achieving a new SOTA on the D4RL benchmark.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 24 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

22 of 24 references.

References · 22

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2022Scalable Diffusion Models with Transformerscited by 6,054
  4. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  5. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  6. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  7. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  8. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  9. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,241
  10. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  11. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 840
  12. 2019Behavior Regularized Offline Reinforcement Learningcited by 662
10 more
  1. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 562
  2. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 516
  3. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  4. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 384
  5. 2022Offline Reinforcement Learning via High-Fidelity Generative Behavior Modelingcited by 182
  6. 2023AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Plannerscited by 149
  7. 2024Simple Hierarchical Planning with Diffusioncited by 73
  8. 2024DiffuserLite: Towards Real-time Diffusion Planningcited by 42
  9. 2024CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Makingcited by 39
  10. 2025What Makes a Good Diffusion Planner for Decision Making?cited by 38

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Refining Compositional Diffusion for Reliable Long-Horizon Planning
  2. 2026RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
  3. 2026Amortizing Trajectory Diffusion with Keyed Drift Fields
  4. 2024Diffusion Models as Optimizers for Efficient Planning in Offline RL
  5. 2025Prior-Guided Diffusion Planning for Offline Reinforcement Learning
  6. 2024Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
  7. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
  8. 2025State-Covering Trajectory Stitching for Diffusion Planners