Skip to content

irom-princeton/llm-backward

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Thinking Forward and Backward: Effective Backward Planning with Large Language Models

Paper

Allen Z. Ren, Brian Ichter, Anirudha Majumdar

Setup

Install dependencies (tested with Python 3.10):

pip install -e .  # setup.py

Set up OpenAI API key and logging directory

export BACKWARD_OPENAI_KEY=<your_key>
export BACKWARD_LOG_DIR=<your_preferred_logging_directory>

Usage

Graph search

Run LLM (with CLI arguments) and then evaluate results

python graph/run.py # see file for CLI arguments
python graph/check_results.py --load_path <logged_pickle_path>

Array transformation (PCFG)

Run LLM (with CLI arguments) and then evaluate results

python pcfg/run.py # see file for CLI arguments
python pcfg/check_results.py --load_path <logged_pickle_path>

License

This repository is released under the MIT license. See LICENSE.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages