policy
MR-DistDeD
DanielBud123 · PyTorch
or hover any field below to flag it
Overview
Name
MR-DistDeD
Author
DanielBud123
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
Model-risk-aware dead-end detection in offline RL via IQN ensembles and Wasserstein ambiguity sets. 2× earlier detection than DistDeD (1.8 vs 0.9 mean lead time) under distribution shift.
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list MR-DistDeD yet.
Datasets that reference this policy
0No datasets reference MR-DistDeD yet.