{"url":"/task/roomenv-v1","name":"RoomEnv-v1","slug":"roomenv-v1","description_markdown":"# The Room environment - v1\r\n\r\n[![DOI](https://img.shields.io/badge/Paper-PDF-red.svg)](https://arxiv.org/abs/2212.02098)\r\n\r\nWe have released a challenging [Gymnasium](https://www.gymlibrary.dev/) compatible\r\nenvironment. The best strategy for this environment is to have both episodic and semantic\r\nmemory systems. See the paper for more information.\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## RoomEnv-v1\r\n\r\n```python\r\nimport gymnasium as gym\r\n\r\nenv = gym.make(\"room_env:RoomEnv-v1\")\r\n(observation, question), info = env.reset()\r\nrewards = 0\r\n\r\nwhile True:\r\n    # There is one different thing in the RoomEnv from the original AAAI-2023 paper:\r\n    # The reward is either +1 or -1, instead of +1 or 0.\r\n    (observation, question), reward, done, truncated, info = env.step(\"This is my answer!\")\r\n    rewards += reward\r\n    if done:\r\n        break\r\n```\r\n\r\n```json\r\n{\r\n    \"des_size\": \"l\",\r\n    \"seed\": 42,\r\n    \"question_prob\": 1.0,\r\n    \"allow_random_human\": False,\r\n    \"allow_random_question\": False,\r\n    \"total_maximum_episode_rewards\": 128,\r\n    \"check_resources\": True,\r\n}\r\n```\r\n\r\nIf you want to create an env with a different set of parameters, you can do so. For example:\r\n\r\n```python\r\nenv_params = {\"seed\": 0,\r\n              \"allow_random_human\": True,\r\n              \"pretrain_semantic\": True}\r\nenv = gym.make(\"room_env:RoomEnv-v1\", **env_params)\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## Data collection\r\n\r\nData is collected from querying ConceptNet APIs. For simplicity, we only collect triples\r\nwhose format is (`head`, `atlocation`, `tail`). Here `head` is one of the 80 MS COCO\r\ndataset categories. This was kept in mind so that later on we can use images as well.\r\n\r\nIf you want to collect the data manually, then run below:\r\n\r\n```\r\npython collect_data.py\r\n```\r\n\r\n## [The RoomDes](room_env/des.py)\r\n\r\nThe DES is part of RoomEnv. You don't have to care about how it works. If you are still\r\ncurious, you can read below.\r\n\r\nYou can run the RoomDes by\r\n\r\n```python\r\nfrom room_env.des import RoomDes\r\n\r\ndes = RoomDes()\r\ndes.run(debug=True)\r\n```\r\n\r\nwith `debug=True` it'll print events (i.e., state changes) to the console.\r\n\r\n```console\r\n{'resource_changes': {'desk': -1, 'lap': 1},\r\n 'state_changes': {'Vincent': {'current_time': 1,\r\n                               'object_location': {'current': 'desk',\r\n                                                   'previous': 'lap'}}}}\r\n{'resource_changes': {}, 'state_changes': {}}\r\n{'resource_changes': {}, 'state_changes': {}}\r\n{'resource_changes': {},\r\n 'state_changes': {'Michael': {'current_time': 4,\r\n                               'object_location': {'current': 'lap',\r\n                                                   'previous': 'desk'}},\r\n                   'Tae': {'current_time': 4,\r\n                           'object_location': {'current': 'desk',\r\n                                               'previous': 'lap'}}}}\r\n```\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://doi.org/10.1609/aaai.v37i1.25075)\r\n\r\n```bibtex\r\n@article{Kim_Cochez_Francois-Lavet_Neerincx_Vossen_2023,\r\n  title={A Machine with Short-Term, Episodic, and Semantic Memory Systems}, volume={37},\r\n  url={https://ojs.aaai.org/index.php/AAAI/article/view/25075},\r\n  DOI={10.1609/aaai.v37i1.25075},\r\n  abstractNote={Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and analyze the behavior of this agent, we designed and released our own reinforcement learning agent environment, “the Room”, where an agent has to learn how to encode, store, and retrieve memories to maximize its return by answering questions. We show that our deep Q-learning based agent successfully learns whether a short-term memory should be forgotten, or rather be stored in the episodic or semantic memory systems. Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.},\r\n  number={1},\r\n  journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Kim, Taewoon and Cochez, Michael and Francois-Lavet, Vincent and Neerincx, Mark and Vossen, Piek},\r\n  year={2023},\r\n  month={Jun.},\r\n  pages={48-56}\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- [Mark Neerincx](https://ocw.tudelft.nl/teachers/m_a_neerincx/)\r\n- [Piek Vossen](https://vossen.info/)\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-v1-on-roomenv-v1","slug":"roomenv-v1-on-roomenv-v1","dataset":"RoomEnv-v1","dataset_url":"/dataset/roomenv-v1","rows_in_archive":2,"metrics":["final agent reward"],"first_row_in_archive_order":{"model":"HumemAI-v0-capacity=32-semantic-pretrained","paper_title":"A Machine with Short-Term, Episodic, and Semantic Memory Systems","paper_url":"/paper/a-machine-with-short-term-episodic-and","paper_date":"2022-12-05","arxiv_id":"2212.02098","code_links":[{"title":"humemai/agent-room-env-v1","url":"https://github.com/humemai/agent-room-env-v1"}],"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/roomenv-v1","name":"RoomEnv-v1","full_name":"The Room environment - v1","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/a-machine-with-short-term-episodic-and","title":"A Machine with Short-Term, Episodic, and Semantic Memory Systems","date":"2022-12-05","arxiv_id":"2212.02098","repositories_listed":1,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}}],"syntology_records":1,"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"}}