Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: jankomp
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 36.4 MB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 1
  • Releases: 0
Created over 1 year ago · Last pushed 8 months ago
Metadata Files
Readme License Citation

README.md

Viualization Interface that enables interactive Reinforcement Learning from Human Feedback

A visualization tool for exploring the behavior space and providing preferences for RLHF.

INSTALLATION

Backend

Build docker image from Dockerfile $ docker build -t interactive-rlhf .

Create container from the docker image named interactive-rlhf $ docker run -it -p 5000:5000 --name interactive-rlhf interactive-rlhf

For later uses when the container is already created: $ docker start interactive-rlhf

Run this command in the terminal to get a bash sessions for the container. $ docker exec -it interactive-rlhf /bin/bash In the container execute this: $ xvfb-run -s "-screen 0 1400x900x24" python3 pairwise_comparison.py or this for the groupwise comparison: $ xvfb-run -s "-screen 0 1400x900x24" python3 pairwise_group_comparison.py

Frontend

Run this command in another terminal: $ git clone https://github.com/jankomp/interactive_rlhf_gui.git $ cd interactive_rlhf_gui $ yarn install $ yarn serve

Owner

  • Login: jankomp
  • Kind: user

Citation (CITATION.bib)

@misc{gleave2022imitation,
  author = {Gleave, Adam and Taufeeque, Mohammad and Rocamonde, Juan and Jenner, Erik and Wang, Steven H. and Toyer, Sam and Ernestus, Maximilian and Belrose, Nora and Emmons, Scott and Russell, Stuart},
  title = {imitation: Clean Imitation Learning Implementations},
  year = {2022},
  howPublished = {arXiv:2211.11972v1 [cs.LG]},
  archivePrefix = {arXiv},
  eprint = {2211.11972},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2211.11972},
}

GitHub Events

Total
  • Public event: 1
  • Push event: 5
Last Year
  • Public event: 1
  • Push event: 5