Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL

Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavior datasets.

Data and Resources

Cite this as

Sungyoon Kim, Yunseon Choi, Daiki E. Matsunaga, Kee-Eung Kim (2024). Dataset: Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL. https://doi.org/10.57702/b0vw4310

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2402.07226
Author Sungyoon Kim
More Authors
Yunseon Choi
Daiki E. Matsunaga
Kee-Eung Kim
Homepage https://github.com/rlatjddbs/SSD