paper-with-me

Papers

Diffusion Models as Optimizers for Efficient Planning in Offline RL

2024-07-23 · Renming Huang, Yunqiang Pei, Guoqing Wang, Yangming Zhang, Yang Yang, Peng Wang, HengTao Shen

Diffusion models have shown strong competitiveness in offline reinforcement learning tasks by formulating decision-making as sequential generation. However, the practicality of these methods is limited due to the lengthy inference processes they require. In this paper, we address this problem by decomposing the sampling process of diffusion models into two decoupled subprocesses: 1) generating a feasible trajectory, which is a time-consuming process, and 2) optimizing the trajectory. With this decomposition approach, we are able to partially separate efficiency and quality factors, enabling us to simultaneously gain efficiency advantages and ensure quality assurance. We propose the Trajectory Diffuser, which utilizes a faster autoregressive model to handle the generation of feasible trajectories while retaining the trajectory optimization process of diffusion models. This allows us to achieve more efficient planning without sacrificing capability. To evaluate the effectiveness and efficiency of the Trajectory Diffuser, we conduct experiments on the D4RL benchmarks. The results demonstrate that our method achieves $\it 3$-$\it 10 \times$ faster inference speed compared to previous sequence modeling methods, while also outperforming them in terms of overall performance. https://github.com/RenMing-Huang/TrajectoryDiffuser Keywords: Reinforcement Learning and Efficient Planning and Diffusion Model

📄 PDF Abstract BibTeX arXiv:2407.16142

Code (1)

renming-huang/trajectorydiffuser 공식 구현 pytorch

Tasks

D4RLDecision MakingOffline RLreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching

2023-06-24 · H. J. Terry Suh, Glen Chou, Hongkai Dai, Lujie Yang 외

Gradient-based methods enable efficient search capabilities in high dimensions. However, in order to apply them effectively in offline optimization paradigms such as offline Reinforcement Learning (RL) or Imitation Learn…

Imitation LearningOffline RLreinforcement-learningReinforcement Learning (RL)

Diffusion Modulation via Environment Mechanism Modeling for Planning

2026-02-23 · Hanping Zhang, Yuhong Guo arxiv

Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional diffusion-based planning methods often fail to account for the fact t…

Reinforcement Learning

What Makes a Good Diffusion Planner for Decision Making?

2025-03-01 · ICLR 2025 3 · Haofei Lu, Dongqi Han, Yifei Shen, Dongsheng Li

Diffusion models have recently shown significant potential in solving decision-making problems, particularly in generating behavior plans -- also known as diffusion planning. While numerous studies have demonstrated th…

Action GenerationDecision MakingDenoisingOffline RL+1

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

2025-07-13 · Guanquan Wang, Takuya Hiraoka, Yoshimasa Tsuruoka 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 opti…

Reinforcement LearningTrajectory Planning

Simple Hierarchical Planning with Diffusion

2024-01-05 · Chang Chen, Fei Deng, Kenji Kawaguchi, Caglar Gulcehre 외

Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing tempora…