{"id":19611927,"url":"https://github.com/princeton-nlp/blindfold-textgame","last_synced_at":"2025-09-12T19:36:57.469Z","repository":{"id":62918209,"uuid":"372397833","full_name":"princeton-nlp/blindfold-textgame","owner":"princeton-nlp","description":"[NAACL 2021] Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents","archived":false,"fork":false,"pushed_at":"2021-05-31T16:52:38.000Z","size":275,"stargazers_count":12,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-27T22:33:45.440Z","etag":null,"topics":["naacl","naacl2021","natural-language-processing","nlp","reinforcement-learning","rl","text-based-game","text-game"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/princeton-nlp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-05-31T05:57:49.000Z","updated_at":"2024-02-29T05:36:22.000Z","dependencies_parsed_at":"2022-11-09T04:49:10.183Z","dependency_job_id":null,"html_url":"https://github.com/princeton-nlp/blindfold-textgame","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/princeton-nlp/blindfold-textgame","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/princeton-nlp%2Fblindfold-textgame","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/princeton-nlp%2Fblindfold-textgame/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/princeton-nlp%2Fblindfold-textgame/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/princeton-nlp%2Fblindfold-textgame/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/princeton-nlp","download_url":"https://codeload.github.com/princeton-nlp/blindfold-textgame/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/princeton-nlp%2Fblindfold-textgame/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274864353,"owners_count":25364231,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-12T02:00:09.324Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["naacl","naacl2021","natural-language-processing","nlp","reinforcement-learning","rl","text-based-game","text-game"],"created_at":"2024-11-11T10:45:05.677Z","updated_at":"2025-09-12T19:36:57.380Z","avatar_url":"https://github.com/princeton-nlp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DRRN Model Variants (Hash input, Inverse dynamics) on Text Games \n\nCode for NAACL 2021 paper [Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents](https://arxiv.org/abs/2103.13552).\n\nProject site: https://blindfolded.cs.princeton.edu\n\n## Getting Started\n\n- Install dependencies:\n```bash\npip install jericho fasttext\n```\n- Run baseline DRRN:\n```python\npython train.py\n```\n\n- Run DRRN (hash):\n```python\npython train.py --hash_rep 1\n```\n\n- Run DRRN (inv-dy):\n```python\npython train.py --w_inv 1 --w_act 1 --r_for 1\n```\n\nUse ``--seed`` to specify game random seed. ``-1`` means episode-varying seeds (stochastic game mode), otherwise game mode is deterministic.\n\nZork I is played by default. More games are [here](https://github.com/princeton-nlp/calm-textgame/tree/master/games) and use ``--rom_path`` to specify which game to play.\n\n## Citation\n```\n@inproceedings{yao2021blindfolded,\n    title={Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents},\n    author={Yao, Shunyu and Narasimhan, Karthik and Hausknecht, Matthew},\n    booktitle={North American Association for Computational Linguistics (NAACL)},\n    year={2021}\n}\n```\n## Acknowledgements\nThe code borrows from [TDQN](https://github.com/microsoft/tdqn). \n\nFor any questions please contact Shunyu Yao `\u003cshunyuyao.cs@gmail.com\u003e`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprinceton-nlp%2Fblindfold-textgame","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprinceton-nlp%2Fblindfold-textgame","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprinceton-nlp%2Fblindfold-textgame/lists"}