python run_env.py --domain {YOUR_DOMAIN} --sample_traj_method {YOUR_TS} --infer_cnf_method {YOUR_ASG}

bash run.sh

psalm
 └─run_env.py                         (the main python script)
 └─run.sh                         (the main experiment script)
 └─keys
    └─ openai_keys.txt             (you should place your openai keys here, one line each)
 └─domains                         (the generated domain files)
    └─ barman
        └─ description_geneator.py (generating natural language description)
        └─ p_example.nl            (example natural language)
        └─ p_example.pddl          (example problem pddl file)
        └─ p_example.sol           (example problem solution file)
        └─ p_example.sol_pddl      (example problem solution file in pddl)
        └─ domain.pddl             (the shared domain.pddl file for all problems)
        └─ xxx.nl                  (task natural language description)
        └─ xxx.pddl                (ground-truth problem pddl, might not be used)
    └─ blocksworld
    └─ floortile
    └─ grippers
    └─ storage
    └─ termes
    └─ tyreworld
 └─prompt                          (the prompt files)
    └─ xxx.txt
    └─ ...
 └─downwards                       (the directory for fast-downward C++ code and build)
    └─ ...
 └─experiments                     (the experiment files)
    └─ ...

@article{zhu2024languagemodelsinferaction,
      title={Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback}, 
      author={Wang Zhu and Ishika Singh and Robin Jia and Jesse Thomason},
      booktitle={Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)}
      year={2024}
}