[LLM4Robot]

==============================

LLM4Robot is a modular high-level library for end-to-end development in embodied AI, which based on Habitat 2.0.

Table of contents

1. Installation
2. Testing

Installation

1. Preparing conda env

   Assuming you have conda installed, let's prepare a conda env:

   # We require python>=3.9 and cmake>=3.14
   conda create -n llm4robot python=3.9 cmake=3.14.0
   conda activate llm4robot

2. conda install habitat-sim

   • To install habitat-sim with bullet physics

     conda install habitat-sim=0.2.4 withbullet -c conda-forge -c aihabitat
     

     See Habitat-Sim's installation instructions for more details.

3. Create a soft link for habitat-lab. The habitat-lab version currently supported is 0.2.4

   pip install -e habitat-lab  # install habitat_lab

4. Create a soft link for habitat-baselines. The habitat-baselines version currently supported is 0.2.4

   pip install -e habitat-baselines  # install habitat_baselines

5. Download Dataset. It is recommended to download in the habitat default way

   python test/example.py

6. Missing basic packages To check and install some dependencies in the Dockerfile

Testing

1. Non-interactive testing: Test the Pick task: Run the example pick task script

   python test/example.py

Related Work

This repo is intended to serve as a foundation with which you can reproduce the results of the experiments detailed in our paper, Large language model as a policy teacher for training reinforcement learning agents

Demonstrate

episode.21._0.-composite_success.1-num_steps.389.mp4