paper-with-me

Papers

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 that generating trajectories in RL requires unique consistency between transitions to ensure coherence in real environments. This oversight can result in considerable discrepancies between the generated trajectories and the underlying mechanisms of a real environment. To address this problem, we propose a novel diffusion-based planning method, termed as Diffusion Modulation via Environment Mechanism Modeling (DMEMM). DMEMM modulates diffusion model training by incorporating key RL environment mechanisms, particularly transition dynamics and reward functions. Experimental results demonstrate that DMEMM achieves state-of-the-art performance for planning with offline reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2602.20422

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

2025-01-26 · Yinan Zheng, Ruiming Liang, Kexin Zheng, Jinliang Zheng 외

Achieving human-like driving behaviors in complex open-world environments is a critical challenge in autonomous driving. Contemporary learning-based planning approaches such as imitation learning methods often struggle t…

Autonomous DrivingImitation Learning

Valdi: Value Diffusion World Models

2026-07-01 · Christopher Lindenberg, Kashyap Chitta hf

World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive enough to represent uncertain futures. Diffusion models offer a natural…

Constrained Generative Modeling with Manually Bridged Diffusion Models

2025-02-27 · Saeid Naderiparizi, Xiaoxuan Liang, Berend Zwartsenberg, Frank Wood

In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practic…

Autonomous Vehicles

A Diffusion-Refined Planner with Reinforcement Learning Priors for Confined-Space Parking

2025-10-15 · Mingyang Jiang, Yueyuan Li, Jiaru Zhang, Songan Zhang 외 arxiv

The growing demand for parking has increased the need for automated parking planning methods that can operate reliably in confined spaces. In restricted and complex environments, high-precision maneuvers are required to …

Reinforcement Learning

SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Driving

2026-04-13 · Haojie Bai, Aimin Li, Ruoyu Yao, Xiongwei Zhao 외 arxiv

Cooperative driving is a safety- and efficiency-critical task that requires the coordination of diverse, interaction-realistic multi-agent trajectories. Although existing diffusion-based methods can capture multimodal be…

Reinforcement Learning