policy
wordgen_curiosity
eremissimo · PyTorch
or hover any field below to flag it
Overview
Name
wordgen_curiosity
Author
eremissimo
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Checking out an idea of using curiosity intrinsic reward in RL tuning of language models to get more variability in the sampling output
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 wordgen_curiosity yet.
Datasets that reference this policy
0No datasets reference wordgen_curiosity yet.