{"url":"/dataset/roomenv-v2","name":"RoomEnv-v2","full_name":"The Room environment - 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\"\"\"\"\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/)","description_withheld":null,"homepage":"https://github.com/humemai/room-env","introduced_date":"2024-08-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/leveraging-knowledge-graph-based-human-like","title":"Leveraging Knowledge Graph-Based Human-Like Memory Systems to Solve Partially Observable Markov Decision Processes","first_author":"Taewoon Kim","url":null},"license":{"name":"MIT","url":"https://github.com/humemai/room-env?tab=MIT-1-ov-file"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Reinforcement Learning (RL)","url":"/task/reinforcement-learning-1","datasets_with_task":"/datasets/task/reinforcement-learning-1"},{"name":"RoomEnv-v2","url":"/task/roomenv-v2","datasets_with_task":"/datasets/task/roomenv-v2"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RoomEnv-v2"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/roomenv-v2-on-roomenv-v2","task":"RoomEnv-v2","dataset_variant":"RoomEnv-v2","rows":2,"metrics":["final agent reward"],"first_row_in_archive_order":{"model":"HumemAI-capacity=48","paper":"/paper/leveraging-knowledge-graph-based-human-like","metrics":{"final agent reward":"235"},"code_links":[{"title":"humemai/agent-room-env-v2-lstm","url":"https://github.com/humemai/agent-room-env-v2-lstm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}