Skip to content

scaliaven/RL4VLM

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

44 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DSGA-3001 Reinforcement Learning Final Project

gym-junqi & Vision/Language/Tensor A2C_PPO

Installation

conda create -n junqi python=3.10.0
conda activate junqi
pip install -r requirements.txt
pip install -e ./LLaVA
pip install -e ./gym-cards

Play

cd RL4VLM/gym-junqi/gym_junqi
python examples/game_mode.py

Training

cd RL4VLM/VLM_PPO/scripts
bash run_nl.sh

About

A Modified Project Based on Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages