policy
MURA-RL-DeepEnsembleV2-82.4
blahmin · RLlib
or hover any field below to flag it
Overview
Name
MURA-RL-DeepEnsembleV2-82.4
Author
blahmin
Framework
RLlib
License
unknown
Skill type
other
Evidence level
untested
Task description
MURA-RL-DeepEnsembleV2-82.4 is an RL-enhanced ensemble model for X-ray fracture identification, inspired by DeepSeek-R1’s reward-driven reinforcement learning. It combines three CNNs with an RL-based weighting agent, achieving 82.4% validation accuracy and 0.65 Cohen’s Kappa score. Pretrained weight
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 MURA-RL-DeepEnsembleV2-82.4 yet.
Datasets that reference this policy
0No datasets reference MURA-RL-DeepEnsembleV2-82.4 yet.