policy
rlvr-grpo-reward-functions
waycodes · PyTorch
or hover any field below to flag it
Overview
Name
rlvr-grpo-reward-functions
Author
waycodes
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Reproducible RLVR post-training reference implementation for open reasoning models centered on GRPO-style online RL and verifiable, auditable reward functions (math/code/tool-use).
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 rlvr-grpo-reward-functions yet.
Datasets that reference this policy
0No datasets reference rlvr-grpo-reward-functions yet.