{"url":"/dataset/nethack-learning-environment","name":"NetHack Learning Environment","full_name":"NetHack Learning Environment","description_markdown":"The **NetHack Learning Environment** (NLE) is a Reinforcement Learning environment based on NetHack 3.6.6. It is designed to provide a standard reinforcement learning interface to the game, and comes with tasks that function as a first step to evaluate agents on this new environment.\nNetHack is one of the oldest and arguably most impactful videogames in history, as well as being one of the hardest roguelikes currently being played by humans. It is procedurally generated, rich in entities and dynamics, and overall an extremely challenging environment for current state-of-the-art RL agents, while being much cheaper to run compared to other challenging testbeds. Through NLE, the authors wish to establish NetHack as one of the next challenges for research in decision making and machine learning.\n\nSource: [https://github.com/facebookresearch/nle](https://github.com/facebookresearch/nle)\nImage Source: [https://github.com/facebookresearch/nle](https://github.com/facebookresearch/nle)","description_withheld":null,"homepage":"https://github.com/facebookresearch/nle","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-nethack-learning-environment","title":"The NetHack Learning Environment","first_author":"Heinrich Küttler","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"NetHack Score","url":"/task/score","datasets_with_task":"/datasets/task/score"}],"languages":[],"variants":["NetHack Learning Environment"],"data_loaders":[{"repo":"https://github.com/facebookresearch/nle","url":"https://github.com/facebookresearch/nle","frameworks":[]}],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/score-on-nethack-learning-environment","task":"NetHack Score","dataset_variant":"NetHack Learning Environment","rows":1,"metrics":["Average Score"],"first_row_in_archive_order":{"model":"RND-mon-hum-neu-mal","paper":"/paper/the-nethack-learning-environment","metrics":{"Average Score":"780"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-nethack-learning-environment","title":"The NetHack Learning Environment","date":"2020-06-24","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":3,"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."}