{"id":"nethack-learning-environment-nle--gh-heiner-nle","name":"NetHack Learning Environment (NLE)","url":"https://github.com/heiner/nle","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/nethack-learning-environment-nle--gh-heiner-nle","family":"memory-research","section":"Memory benchmarks & evaluation","sections":["Memory benchmarks & evaluation"],"tier":2,"last_verified_at":"2026-05-14","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":{"storage":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"retrieval":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"persistence":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"update":[{"value":"read-only","primary":true,"reason":null}],"unit":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"governance":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"conflict":[{"value":"n/a","primary":true,"reason":"not applicable — read-only evaluation dataset"}]},"cells":{"type":{"value":"Roguelike RL benchmark — NetHack as agent environment","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"desc":{"value":"DeepMind / FAIR's NetHack Learning Environment — a Gym-compatible interface to NetHack, the canonical roguelike. Massive procedural state space, permadeath, deep item / skill interactions, ASCII partial-observability. Released at NeurIPS 2020; canonical long-horizon partial-observability RL benchmark.","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"claims":{"value":"NeurIPS 2020 paper; NetHack Challenge run at NeurIPS 2021. After 4 years still considered unsolved at expert-human level by autonomous agents.","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"modalities":{"value":"text/ASCII glyph grid + numeric stats","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"created":{"value":"2020-06 (Küttler et al. NeurIPS 2020)","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"latest-release":{"value":"v0.9.x series (active as of 2024)","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"license":{"value":"NetHack General Public License","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"gh":{"value":"1.0k★ Python/C","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"mindshare":{"value":"canonical roguelike RL benchmark; cited by Dreamer, MuZero, IMPALA follow-ups","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citations":{"value":"200+ cites — NeurIPS 2020 paper","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"funding":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"customers":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"pricing":{"value":"not applicable — open benchmark; free to use","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"compliance":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"data-handling":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"deployment":{"value":"not applicable — run locally","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"Heinrich Küttler, Nantas Nardelli, Alexander H. Miller, Roberta Raileanu, Marco Selvatici, Edward Grefenstette, Tim Rocktäschel (FAIR / DeepMind)","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"volume":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"perf":{"value":"not applicable — does not compete on benchmarks","citation":null,"status":"not-applicable","tier":"T3"},"repro":{"value":"Independently reproduced — community NetHack Challenge 2021","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"code-release":{"value":"Code public + game-engine source open","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"api-surface":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"latency":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"throughput":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"backend-storage":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"multi-tenancy":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"encryption":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"sso-rbac":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"embedding-model":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"versioning":{"value":"not applicable — static benchmark","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"tombstoning":{"value":"not applicable — static benchmark","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"schema-evolution":{"value":"not applicable — fixed evaluation dataset","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"namespace":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"contradiction":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"forgetting":{"value":"not applicable — static benchmark","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"mcp-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"a2a-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"otel":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"webhooks":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"import-export":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"integration-count":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"orchestration":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"programmatic-control":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"vendor-benchmarks":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"pricing-specifics":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"agent-abstraction":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"time-to-running":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"anti-fit":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"optimised-for":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"adjacent-infrastructure":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"pros":{"value":"Massive (10^48+) state space + long horizon (10^4-10^5 steps) makes it one of the hardest RL benchmarks; ASCII representation is interpretable; procedural so memorisation cannot solve it.","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"cons":{"value":"Sparse reward + dense procedural complexity → RL still hard-stuck at sub-human levels; ASCII-only modality limits transfer to multimodal agents.","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"links":{"value":"github.com/heiner/nle NeurIPS 2020 paper","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"obs-langsmith":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-opentelemetry":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-datadog":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-helicone":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-weave":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-langfuse":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-arize":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-custom":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-token-budget":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-prompt-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-semantic-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-batching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-model-routing":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-streaming-only":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-observability-cost-attribution":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-langsmith-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-braintrust":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-weights-and-biases-agent":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-helicone-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-custom-test-harness":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-human-loop":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-production-traffic-replay":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"commit-trajectory":{"value":"[{\"ym\":\"2019-11\",\"cum\":8868},{\"ym\":\"2019-12\",\"cum\":8943},{\"ym\":\"2020-01\",\"cum\":8997},{\"ym\":\"2020-03\",\"cum\":9016},{\"ym\":\"2020-05\",\"cum\":9081},{\"ym\":\"2020-06\",\"cum\":9158},{\"ym\":\"2020-07\",\"cum\":9192},{\"ym\":\"2020-08\",\"cum\":9320},{\"ym\":\"2020-09\",\"cum\":9370},{\"ym\":\"2020-10\",\"cum\":9402},{\"ym\":\"2020-11\",\"cum\":9452},{\"ym\":\"2020-12\",\"cum\":9464},{\"ym\":\"2021-01\",\"cum\":9466},{\"ym\":\"2021-02\",\"cum\":9476},{\"ym\":\"2021-03\",\"cum\":9484},{\"ym\":\"2021-05\",\"cum\":9486},{\"ym\":\"2021-06\",\"cum\":9536},{\"ym\":\"2021-07\",\"cum\":9574},{\"ym\":\"2021-08\",\"cum\":9580},{\"ym\":\"2021-09\",\"cum\":9595},{\"ym\":\"2021-10\",\"cum\":9608},{\"ym\":\"2021-11\",\"cum\":9628},{\"ym\":\"2021-12\",\"cum\":9643},{\"ym\":\"2022-01\",\"cum\":9659},{\"ym\":\"2022-02\",\"cum\":9661},{\"ym\":\"2022-04\",\"cum\":9673},{\"ym\":\"2022-05\",\"cum\":9709},{\"ym\":\"2022-06\",\"cum\":9719},{\"ym\":\"2022-08\",\"cum\":9723},{\"ym\":\"2022-09\",\"cum\":9725},{\"ym\":\"2022-11\",\"cum\":9731},{\"ym\":\"2022-12\",\"cum\":9733},{\"ym\":\"2023-01\",\"cum\":9734},{\"ym\":\"2023-08\",\"cum\":9735},{\"ym\":\"2023-11\",\"cum\":9740},{\"ym\":\"2024-01\",\"cum\":9741},{\"ym\":\"2024-05\",\"cum\":9773},{\"ym\":\"2024-06\",\"cum\":9777},{\"ym\":\"2024-07\",\"cum\":9781},{\"ym\":\"2024-10\",\"cum\":9785},{\"ym\":\"2024-11\",\"cum\":9786},{\"ym\":\"2025-02\",\"cum\":9790},{\"ym\":\"2025-03\",\"cum\":9791},{\"ym\":\"2025-04\",\"cum\":9792},{\"ym\":\"2025-05\",\"cum\":9795},{\"ym\":\"2025-07\",\"cum\":9796},{\"ym\":\"2025-08\",\"cum\":9799},{\"ym\":\"2025-09\",\"cum\":9800},{\"ym\":\"2025-12\",\"cum\":9804},{\"ym\":\"2026-02\",\"cum\":9812},{\"ym\":\"2026-03\",\"cum\":9819},{\"ym\":\"2026-04\",\"cum\":9823}]","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"download-trajectory":{"value":"[{\"ym\":\"2025-11\",\"monthly\":4450,\"cum\":4450},{\"ym\":\"2025-12\",\"monthly\":1044,\"cum\":5494},{\"ym\":\"2026-01\",\"monthly\":2406,\"cum\":7900},{\"ym\":\"2026-02\",\"monthly\":2242,\"cum\":10142},{\"ym\":\"2026-03\",\"monthly\":7210,\"cum\":17352},{\"ym\":\"2026-04\",\"monthly\":5865,\"cum\":23217}]","citation":"https://pypi.org/project/nle/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"registry"},"cost-input-usd-per-mtok":{"value":"0","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"cost-tier":{"value":"free","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"cost-pricing-model":{"value":"free-tier","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"cost-last-verified":{"value":"2026-06-29","citation":"https://github.com/heiner/nle","status":"real-data","tier":"T1","source_class":"repo"},"capability-composite-score":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — benchmark environment, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — benchmark environment, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"","citation":null,"status":"no-data","tier":"T3"},"licensing-bucket":{"value":"not applicable — research paper","citation":"https://github.com/heiner/nle","status":"not-applicable","tier":"T1","source_class":"repo"},"positioning-platform-vs-product":{"value":"","citation":null,"status":"no-data","tier":"T3"},"taxonomy-three-layer-rollup":{"value":"agent-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"searched not found","citation":"https://oss.open-digger.cn/github/heiner/nle/openrank.json","status":"depth-floor-reached","tier":"T2","source_class":"third-party"},"freshness-date":{"value":"2026-05-14","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/nethack-learning-environment-nle--gh-heiner-nle","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"","citation":null,"status":"no-data","tier":"T3"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":30,"third_party_cells":0},"edges":{"outgoing":[],"incoming":[]},"history":[],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}