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 yet

Compatible environments

0

No environments list MR-DistDeD yet.

Datasets that reference this policy

0

No datasets reference MR-DistDeD yet.