{"url":"/task/roomenv-v2","name":"RoomEnv-v2","slug":"roomenv-v2","description_markdown":"# The Room environment - v2\r\n\r\n[![DOI](https://img.shields.io/badge/Paper-PDF-red.svg)](https://arxiv.org/pdf/2408.05861)\r\n\r\nWe have released a challenging [Gymnasium](https://www.gymlibrary.dev/) compatible\r\nenvironment. See the paper for more information.\r\n\r\n<img src=\"figures/room-layout-xl.png\" alt=\"\" style=\"width: 50%;\"/><img src=\"figures/room-layout-kg-xl.png\" alt=\"\" style=\"width: 50%;\"/>\r\n\r\n## Prerequisites\r\n\r\n1. A unix or unix-like x86 machine\r\n1. python 3.10 or higher.\r\n1. Running in a virtual environment (e.g., conda, virtualenv, etc.) is highly recommended so that you don't mess up with the system python.\r\n1. This env is added to the PyPI server. Just run: `pip install room-env`\r\n\r\n## Creating a RoomEnv-v2\r\n\r\n```python\r\nimport random\r\nfrom room_env.create_room_v2 import RoomCreator\r\n\r\nroom_creator = RoomCreator(\r\n    filename=\"dev\",\r\n    grid_length=7,\r\n    num_rooms=32,\r\n    num_static_objects=8,\r\n    num_independent_objects=8,\r\n    num_dependent_objects=8,\r\n    room_prob=0.5,\r\n    minimum_transition_stay_prob=0.6,\r\n    static_object_in_every_room=False,\r\n    give_fake_names=False,\r\n)\r\nroom_creator.run()\r\n```\r\n\r\n[`./room-env-v2.ipynb`](./room-env-v2.ipynb) has some good examples.\r\n\r\n## Running a RoomEnv-v2\r\n\r\n```python\r\nimport gymnasium as gym\r\nimport random\r\n\r\nenv = gym.make(\"room_env:RoomEnv-v2\", room_size=\"l\")\r\nobservations, info = env.reset()\r\nrewards = 0\r\n\r\nwhile True:\r\n    observations, reward, done, truncated, info = env.step(\r\n        (\r\n            [\"random answer\"] * len(observations[\"questions\"]),\r\n            random.choice([\"north\", \"east\", \"south\", \"west\", \"stay\"]),\r\n        )\r\n    )\r\n    rewards += reward\r\n    if done or truncated:\r\n        break\r\n\r\n# You can also get the map of the rooms\r\nroom_layout = env.unwrapped.return_room_layout(exclude_walls=True)\r\n```\r\n\r\nTake a look at [this repo](https://github.com/humemai/humemai) for an actual\r\ninteraction with this environment to learn a policy.\r\n\r\n## Contributing\r\n\r\nContributions are what make the open source community such an amazing place to be learn,\r\ninspire, and create. Any contributions you make are **greatly appreciated**.\r\n\r\n1. Fork the Project\r\n1. Create your Feature Branch (`git checkout -b feature/AmazingFeature`)\r\n1. Run `make test && make style && make quality` in the root repo directory,\r\n   to ensure code quality.\r\n1. Commit your Changes (`git commit -m 'Add some AmazingFeature'`)\r\n1. Push to the Branch (`git push origin feature/AmazingFeature`)\r\n1. Open a Pull Request\r\n\r\n## [Cite our paper](https://arxiv.org/abs/2408.05861)\r\n\r\n```bibtex\r\n@misc{kim2024leveragingknowledgegraphbasedhumanlike,\r\n      title={Leveraging Knowledge Graph-Based Human-Like Memory Systems to Solve Partially Observable Markov Decision Processes},\r\n      author={Taewoon Kim and Vincent François-Lavet and Michael Cochez},\r\n      year={2024},\r\n      eprint={2408.05861},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.AI},\r\n      url={https://arxiv.org/abs/2408.05861},\r\n}\r\n```\r\n\r\n## Authors\r\n\r\n- [Taewoon Kim](https://taewoon.kim/)\r\n- [Michael Cochez](https://www.cochez.nl/)\r\n- [Vincent Francois-Lavet](http://vincent.francois-l.be/)\r\n\r\n## License\r\n\r\n[MIT](https://choosealicense.com/licenses/mit/)","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1,"papers_with_code":1,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/roomenv-v2-on-roomenv-v2","slug":"roomenv-v2-on-roomenv-v2","dataset":"RoomEnv-v2","dataset_url":"/dataset/roomenv-v2","rows_in_archive":2,"metrics":["final agent reward"],"first_row_in_archive_order":{"model":"HumemAI-capacity=48","paper_title":"Leveraging Knowledge Graph-Based Human-Like Memory Systems to Solve Partially Observable Markov Decision Processes","paper_url":"/paper/leveraging-knowledge-graph-based-human-like","paper_date":"2024-08-11","arxiv_id":"2408.05861","code_links":[{"title":"humemai/agent-room-env-v2-lstm","url":"https://github.com/humemai/agent-room-env-v2-lstm"}],"syntology":null}}],"datasets":[{"url":"/dataset/roomenv-v2","name":"RoomEnv-v2","full_name":"The Room environment - v2","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":1,"of":1,"tagged_in_all":1,"items":[{"url":"/paper/leveraging-knowledge-graph-based-human-like","title":"Leveraging Knowledge Graph-Based Human-Like Memory Systems to Solve Partially Observable Markov Decision Processes","date":"2024-08-11","arxiv_id":"2408.05861","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}