mlsanityData to 14 Oct 2026

Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning

arXiv 2507.09534 ↗First posted 13 Jul 2025cs.AI cs.LG cs.ROcited by 2

On the map: Offline RL and imitation learning from data → Diffusion and flow policies for offline RL

Abstract (arXiv)

This paper introduces Consistency Trajectory Planning (CTP), a novel offline model-based reinforcement learning method that leverages the recently proposed Consistency Trajectory Model (CTM) for efficient trajectory optimization. While prior work applying diffusion models to planning has demonstrated strong performance, it often suffers from high computational costs due to iterative sampling procedures. CTP supports fast, single-step trajectory generation without significant degradation in policy quality. We evaluate CTP on the D4RL benchmark and show that it consistently outperforms existing diffusion-based planning methods in long-horizon, goal-conditioned tasks. Notably, CTP achieves higher normalized returns while using significantly fewer denoising steps. In particular, CTP achieves comparable performance with over 120× speedup in inference time, demonstrating its practicality and effectiveness for high-performance, low-latency offline planning.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for offline RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 44 of its 52 references that are in the map. First posted on arXiv 13 Jul 2025.

Builds on

44 of 52 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation9 Jun
  2. 2025What Makes a Good Diffusion Planner for Decision Making?1 Mar
  3. 2023Learning a Diffusion Model Policy from Rewards via Q-Score Matching18 Dec
  4. 2023Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning29 Sep
  5. 2023Efficient Diffusion Policies for Offline Reinforcement Learning31 May
  6. 2023IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies20 Apr
  7. 2023AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners3 Feb
  8. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov
  9. 2022Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling29 Sep
  10. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning12 Aug

Other references · 34

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  10. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  11. 2023Consistency Modelscited by 1,822
  12. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
22 more
  1. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  2. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  3. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  4. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  5. 2023Learning Universal Policies via Text-Guided Video Generationcited by 522
  6. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 459
  7. 2023Improved Techniques for Training Consistency Modelscited by 439
  8. 2023Imitating Human Behaviour with Diffusion Modelscited by 263
  9. 2016Learning to Poke by Poking: Experiential Learning of Intuitive Physicscited by 154
  10. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 148
  11. 2018Zero-Shot Visual Imitationcited by 117
  12. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learningcited by 115
  13. 2023Synthetic Experience Replaycited by 101
  14. 2024Diffusion Actor-Critic with Entropy Regulatorcited by 94
  15. 2024Simple Hierarchical Planning with Diffusioncited by 73
  16. 2024Policy-Guided Diffusioncited by 41
  17. 2023AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Modelcited by 37
  18. 2023World Models via Policy-Guided Trajectory Diffusioncited by 34
  19. 2024AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimizationcited by 19
  20. 2024Model-based Offline Reinforcement Learning with Lower Expectile Q-Learningcited by 17
  21. 2024Sampling from Energy-based Policies using Diffusioncited by 17
  22. 2023Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertaintycited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Improving Diffusion Planners by Self-Supervised Action Gating with Energiescited by 1
  2. 2026Shortcut Trajectory Planning for Efficient Offline Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models as Optimizers for Efficient Planning in Offline RL
  2. 2021Model-Based Offline Planning with Trajectory Pruning
  3. 2026Amortizing Trajectory Diffusion with Keyed Drift Fields
  4. 2026Discrete Flow Matching for Offline-to-Online Reinforcement Learning
  5. 2023Boosting Continuous Control with Consistency Policy
  6. 2025Offline Reinforcement Learning with Generative Trajectory Policies
  7. 2025Prior-Guided Diffusion Planning for Offline Reinforcement Learning
  8. 2025Controllable Flow Matching for Online Reinforcement Learning