policy
VinePPO
Asimawad · PyTorch
or hover any field below to flag it
Overview
Name
VinePPO
Author
Asimawad
Framework
PyTorch
License
Apache-2.0
Skill type
navigation
Evidence level
untested
Task description
This repository contains an experimental implementation of **Fine-Grained Credit Assignment for RL Training (CAL)** on top of Google's Tunix framework. This research explores token-level reward assignment to improve training stability and sample efficiency in reinforcement learning for large languag
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 VinePPO yet.
Datasets that reference this policy
0No datasets reference VinePPO yet.