hea1or / llm-planner Goto Github PK

View Code? Open in Web Editor NEW

[ICCV'23] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

License: MIT License

Shell 0.09% Python 56.82% C 34.68% Makefile 0.09% Yacc 2.34% Lex 0.32% PDDL 5.66%

llm-planner's Introduction

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

Code for LLM-Planner.

Check project website for an overview and a demo.

News:

Dec 23: LLM-Planner with support for an oracle low-level planner with a new easy-setup framework with ALFOWLRD backbone. We hope this codebase can serve as a foundation for building LLM or LMM based methods with ALFRED.

Release process:

Quickstart

Clone repo:

git clone https://github.com/OSU-NLP-Group/LLM-Planner
cd LLM-Planner
export ALFWORLD_DATA="$(pwd)/alfworld/data"

Install requirements:

# Conda or Python enviornment recommended 
# Install requirements for the AI2Thor simulator and ALFRED
cd alfworld
pip install .
# Install requirements for LLM-Planner
cd ../src
pip install -r requirements.txt

Download data:

cd ../alfworld
alfworld-download

Sanity check on AI2Thor simulator

python scripts/check_thor.py
# This should return successful, if not your AI2Thor simulator is not set up correctly.

Start evaluation with GPT-4

export OPENAI_KEY=<Your OpenAI Key>
cd ../src
python run_eval.py --config gpt4_base_config.yaml

Common Questions and Answers

Coming soon.

Hardware

Tested on:

Mac M1
Ubuntu 18.04

Citation Information

If you find this code useful, please consider citing our paper:

@InProceedings{song2023llmplanner,
  author    = {Song, Chan Hee and Wu, Jiaman and Washington, Clayton and Sadler, Brian M. and Chao, Wei-Lun and Su, Yu},
  title     = {LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  year      = {2023},
}