{"url":"/task/score","name":"NetHack Score","slug":"score","description_markdown":"Mean in-game score over 1000 episodes with random seeds not seen during training. See https://arxiv.org/abs/2006.13760 (Section 2.4 Evaluation Protocol) for details.","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"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/score-on-nethack-learning-environment","slug":"score-on-nethack-learning-environment","dataset":"NetHack Learning Environment","dataset_url":"/dataset/nethack-learning-environment","rows_in_archive":1,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"RND-mon-hum-neu-mal","paper_title":"The NetHack Learning Environment","paper_url":"/paper/the-nethack-learning-environment","paper_date":"2020-06-24","arxiv_id":"2006.13760","code_links":[{"title":"facebookresearch/nle","url":"https://github.com/facebookresearch/nle"},{"title":"Pieter-Cawood/Reinforcement-Learning","url":"https://github.com/Pieter-Cawood/Reinforcement-Learning"},{"title":"Sarah-wookey/RL_NetHack_2020","url":"https://github.com/Sarah-wookey/RL_NetHack_2020"}],"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":3}}}],"datasets":[{"url":"/dataset/nethack-learning-environment","name":"NetHack Learning Environment","full_name":"NetHack Learning Environment","num_papers_in_archive":23}],"subtasks":[],"parent_tasks":[{"url":"/task/nethack","name":"NetHack"}],"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/the-nethack-learning-environment","title":"The NetHack Learning Environment","date":"2020-06-24","arxiv_id":"2006.13760","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":3}}],"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"}}