Cite
Notes
Only stored in your browser.
Attribution
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
arXiv 2026
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
arXiv 2024
from 2 papers
Dongbin Zhao
Chunlin Chen
Haohuan Huang
Kaiwen Jiang
Li Zhang
Wenhao Wu
Yuqian Fu
Zhi Wang