{"id":28516893,"url":"https://github.com/borealisai/llm-pddl-planning","last_synced_at":"2026-01-31T14:04:16.869Z","repository":{"id":278641992,"uuid":"880615762","full_name":"BorealisAI/llm-pddl-planning","owner":"BorealisAI","description":null,"archived":false,"fork":false,"pushed_at":"2025-02-20T21:11:20.000Z","size":121,"stargazers_count":9,"open_issues_count":0,"forks_count":2,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-06-09T04:16:06.297Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"PDDL","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BorealisAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-10-30T03:03:32.000Z","updated_at":"2025-06-06T06:36:37.000Z","dependencies_parsed_at":"2025-02-20T22:23:29.064Z","dependency_job_id":"a5f13c76-aa07-4c84-8b92-b5fc8a1f64b4","html_url":"https://github.com/BorealisAI/llm-pddl-planning","commit_stats":null,"previous_names":["borealisai/llm-pddl-planning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/BorealisAI/llm-pddl-planning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fllm-pddl-planning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fllm-pddl-planning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fllm-pddl-planning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fllm-pddl-planning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BorealisAI","download_url":"https://codeload.github.com/BorealisAI/llm-pddl-planning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorealisAI%2Fllm-pddl-planning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28944789,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-31T13:02:32.153Z","status":"ssl_error","status_checked_at":"2026-01-31T13:00:07.528Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-06-09T04:13:19.629Z","updated_at":"2026-01-31T14:04:16.863Z","avatar_url":"https://github.com/BorealisAI.png","language":"PDDL","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [Neurips 2024] Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models\n\n[![arXiv](https://img.shields.io/badge/arXiv-2407.12979-b31b1b.svg)](https://arxiv.org/abs/2407.12979)\n\nThis is the official Repository to the paper [Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models](https://arxiv.org/abs/2407.12979).\n\n## Quick Run\n\nTo reproduce the experiments in our paper, follow below steps:\n\n1. Prepare the data. You can obtain the original PDDL files from the [LLM+P repository](https://github.com/Cranial-XIX/llm-pddl) and [DownwardBenchmarks repository](https://github.com/aibasel/downward-benchmarks). We provide the pddl files for some of the environments in the `data` folder. You can then produce the back translations, templates, and descriptions using the files `back_translate.py, gen_pddl_template_pddl.py`.\n\n2. Install the python requirements via \n```bash\npip install requirements.txt\n```\n**Note:** requires Python \u003e= 3.9\n\n3. Download the following external libraries:\n\n* [VAL](https://github.com/KCL-Planning/VAL)\n* [Fast Downward 22.06.1](https://github.com/aibasel/downward/releases/tag/release-22.06.1)\n\n4. Configure the following environment variables in `reproduce.sh`: `FD_PY_PATH` (path to the .py file of fast downard), `VAL_BIN_PATH` (path to the VAL library binary file), `OPENAI_API_KEY` (OpenAI key), `WANDB_ENTITY` (wandb entity), `WANDB_PROJECT` (wandb project). We use the `gpt-4-1106-preview` GPT4 model in our project by default.\n\n6. Run \n```\nbash reproduce.sh\n```\nto reproduce the experiments.\n\n\n## Repository Structure\n\nThe data used in our experiments can be found in the `data` directory. Each domain has the following format:\n\n```\n📦domain\n ├ 📜domain.pddl               # The domain PDDL file\n ├ 📜domain_template.pddl      # Domain template PDDL\n ├ 📜domain.nl                 # Natural language description of the domain (GPT-generated).\n ├ 📜predicate_descriptor.py   # Mapping between NL descriptions and predicates (GPT-generated).\n ├ 📜p{i}.pddl                 # The {i}-th problem PDDL file\n ├ 📜p{i}_template.pddl        # The {i}-th problem template \n ├ 📜p{i}.nl                   # Natural language description of the {i}-th problem (GPT-generated).\n ├ 📜p_example.pddl            # Example problem PDDL file.\n ├ 📜p_example_template.pddl   # Example problem template.\n ├ 📜p_example.nl              # Example natural language description.\n └ 📜p_example.sol             # Example solution.\n```\n\nThe following is the code structure for source files:\n```\n📦src\n ├ 📜back_translate.py         # Backtranslation utils for domain/problem/description natural language geneation\n ├ 📜domains.py              \n ├ 📜error_messages.py        \n ├ 📜evaluation.py            \n ├ 📜gen_pddl_template_pddl.py # Generates PDDL templates from the original PDDL files.\n ├ 📜gpt_client.py            \n ├ 📜intrinsic_planning.py     # Intrinsic planning baselines\n ├ 📜main.py                   # Main entry point for our method\n ├ 📜pddl_utils.py             # Utility functions to work with PDDL files.\n ├ 📜planning.py               # Core planning logic and functions.\n ├ 📜problem_domain_translation.py\n ├ 📜prompts.py               \n ├ 📂rw_analysis              # Analysis for exploration walk\n │  ├ 📜rw_analysis.py        # Core reward analysis logic.\n │  └ 📜rw_corr_plot.py       # Plots for reward correlation analysis.\n └ 📜utils.py \n```\n\n\n## Citation\n\nIf you find this work useful, please cite our paper:\n```\n@inproceedings{\n  mahdavi2024leveraging,\n  title={Leveraging Environment Interaction for Automated {PDDL} Translation and Planning with Large Language Models},\n  author={Sadegh Mahdavi and Raquel Aoki and Keyi Tang and Yanshuai Cao},\n  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},\n  year={2024},\n  url={https://openreview.net/forum?id=RzlCqnncQv}\n}\n```\n\n## Questions/Bugs\n\nPlease submit a Github issue or contact smahdavi@ece.ubc.ca if you have any questions or find any bugs.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborealisai%2Fllm-pddl-planning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fborealisai%2Fllm-pddl-planning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborealisai%2Fllm-pddl-planning/lists"}