policy

RLHF-Reward-Optimization

prtk1729 · PyTorch

or hover any field below to flag it

Overview

Name
RLHF-Reward-Optimization
Author
prtk1729
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
A modular and scalable Reinforcement Learning with Human Feedback (RLHF) pipeline for fine-tuning language models using reward models. Implements PPO-based RL training with reward model optimization from ranked datasets (IMDb sentiment). Designed for reproducibility and extensibility.

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 RLHF-Reward-Optimization yet.

Datasets that reference this policy

0

No datasets reference RLHF-Reward-Optimization yet.