policy

module-reward-models

m-serious · PyTorch

or hover any field below to flag it

Overview

Name
module-reward-models
Author
m-serious
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
This project implements a multi-module reward model training system designed to further RL finetune agent performance across complex multi-turn tasks.

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 module-reward-models yet.

Datasets that reference this policy

0

No datasets reference module-reward-models yet.