nle/score
Score progression
Maximize progress and score through a long-horizon seeded episode.
NLE observationgame action
Not yet importedRequires sandbox
NetHack Learning Environment
Upstream publisher Meta AI Researchfacebookresearch/nle
A standardized interface to a procedurally generated, partially observed, system-rich, and extremely long-horizon game.
simulationlong-horizongamessandbox
PROVENANCEUPSTREAM RECORD
- Upstream source
- facebookresearch/nle
- Trunchbull port
- Not packaged
- Version
- UPSTREAM
- Release digest
- Not compiled
- License
- MIT
Source commit: Upstream head not pinnedPublished Indexed July 30, 2026
WHAT THIS PROJECT MEASURES
README
NLE exposes NetHack tasks and observations for agents. Useful evaluation should report progression and task-level rewards rather than treating full ascension as the only success signal.
The environment is a poor first integration: episodes are long, failures are difficult to explain, and reproducible replay requires careful seed, action, and state capture.
EXECUTION CONTRACT
Requires long-lived seeded sandboxes, NLE observations and actions, progression metrics, and replayable episodes.
TRUNCHBULL AVAILABILITY
Import status
Not yet imported
Not yet imported. Build on a proven MiniHack adapter and publish task-level progression rather than one ascension score.
1 CASES
Evaluation cases
1
Requires sandbox
2 REQUESTED TOOLS
Tools
2
NLE observation
sandboxReturns structured and language-wrapped NetHack state.
Required
game action
sandboxSubmits discrete actions to the active episode.
Required
MACHINE-READABLE PROVENANCE
Registry record
{
"name": "NetHack Learning Environment",
"catalogOwner": null,
"source": {
"url": "https://github.com/facebookresearch/nle",
"version": "Upstream project",
"commit": "Upstream head not pinned",
"license": "MIT"
},
"port": null,
"release": {
"digest": "Not compiled",
"lane": "sandbox",
"sandboxRequired": true
},
"cases": [
"nle/score"
],
"tools": [
"NLE observation",
"game action"
]
}BUILD ON THIS PROJECT