Imagen de Portada

DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Guanghe, Shan, Yixiang, Zhu, Zhengbang, Long, Ting, Zhang, Weinan
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning
por: Baek, Seungho, et al.
Publicado: (2025)

State-Covering Trajectory Stitching for Diffusion Planners
por: Lee, Kyowoon, et al.
Publicado: (2025)

R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning
por: Chen, Zhuokun, et al.
Publicado: (2025)

Generative Trajectory Stitching through Diffusion Composition
por: Luo, Yunhao, et al.
Publicado: (2025)

Treatment Stitching with Schrödinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies
por: Shin, Dong-Hee, et al.
Publicado: (2025)

Improving Trajectory Stitching with Flow Models
por: O'Mahoney, Reece, et al.
Publicado: (2025)

MADiff: Offline Multi-agent Learning with Diffusion Models
por: Zhu, Zhengbang, et al.
Publicado: (2023)

ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts
por: Yu, Hang, et al.
Publicado: (2025)

Diffusion Models for Reinforcement Learning: A Survey
por: Zhu, Zhengbang, et al.
Publicado: (2023)

Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
por: Mao, Liyuan, et al.
Publicado: (2024)

Stitched Value Model for Diffusion Alignment
por: Go, Hyojun, et al.
Publicado: (2026)

Generative Panoramic Image Stitching
por: Tuli, Mathieu, et al.
Publicado: (2025)

Is Temporal Difference Learning the Gold Standard for Stitching in RL?
por: Bortkiewicz, Michał, et al.
Publicado: (2025)

DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning
por: Zhao, Hanye, et al.
Publicado: (2024)

Heterogeneity-Aware Coordination for Federated Learning via Stitching Pre-trained blocks
por: Zhan, Shichen, et al.
Publicado: (2024)

Context-Former: Stitching via Latent Conditioned Sequence Modeling
por: Zhang, Ziqi, et al.
Publicado: (2024)

Offline Trajectory Optimization for Offline Reinforcement Learning
por: Zhao, Ziqi, et al.
Publicado: (2024)

Contrastive Diffuser: Planning Towards High Return States via Contrastive Learning
por: Shan, Yixiang, et al.
Publicado: (2024)

Multiple Object Stitching for Unsupervised Representation Learning
por: Shen, Chengchao, et al.
Publicado: (2025)

Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL
por: Kim, Sungyoon, et al.
Publicado: (2024)

Stitch: Training-Free Position Control in Multimodal Diffusion Transformers
por: Bader, Jessica, et al.
Publicado: (2025)

DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models
por: Zhang, Shenyu, et al.
Publicado: (2025)

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
por: Tu, Songjun, et al.
Publicado: (2024)

Robust Offline Imitation Learning Through State-level Trajectory Stitching
por: Wang, Shuze, et al.
Publicado: (2025)

Mapping representations in Reinforcement Learning via Semantic Alignment for Zero-Shot Stitching
por: Ricciardi, Antonio Pio, et al.
Publicado: (2025)

Revisiting Model Stitching In the Foundation Model Era
por: Mai, Zheda, et al.
Publicado: (2026)

Offline Reinforcement Learning with Generative Trajectory Policies
por: Feng, Xinsong, et al.
Publicado: (2025)

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
por: Pan, Zizheng, et al.
Publicado: (2024)

Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
por: Grover, Shivam, et al.
Publicado: (2024)

KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
por: Sanyal, Debopam, et al.
Publicado: (2026)

(Almost) Free Modality Stitching of Foundation Models
por: Singh, Jaisidh, et al.
Publicado: (2025)

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay
por: Liu, Jinmei, et al.
Publicado: (2024)

Offline Safe Reinforcement Learning Using Trajectory Classification
por: Gong, Ze, et al.
Publicado: (2024)

Policy-Based Trajectory Clustering in Offline Reinforcement Learning
por: Hu, Hao, et al.
Publicado: (2025)

TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning
por: Sestini, Alessandro, et al.
Publicado: (2025)

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
por: Huang, Xiao, et al.
Publicado: (2025)

StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
por: Li, Bingyu, et al.
Publicado: (2024)

DiffMove: Group Mobility Tendency Enhanced Trajectory Recovery via Diffusion Model
por: Long, Qingyue, et al.
Publicado: (2025)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
por: Zhang, Tianle, et al.
Publicado: (2024)

GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
por: Lee, Jaewoo, et al.
Publicado: (2024)