Skip to content
Back to skills

Katakomba Tools And Benchmarks For Datadriven Nethack

ASecurity

**arXiv ID:** 2306.08772 **Authors:** Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov **Published:** 2023-06-14T22:50:25Z **Abstract:** NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions. One of the promising directions for a breakthrough is using pre-collected datasets similar to recent developments in robotics, recommender systems, and more under the umbrella of offline reinf...

  • 3 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added September 11, 2026
tools

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill katakomba-tools-and-benchmarks-for-datadriven-nethack --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Katakomba Tools And Benchmarks For Datadriven Nethack?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Katakomba Tools And Benchmarks For Datadriven Nethack
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-katakomba-tools-and-benchmarks-for-datadriven-neth/badge)](https://www.skillsdirectory.com/skills/hiyenwong-katakomba-tools-and-benchmarks-for-datadriven-neth)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Katakomba: Tools and Benchmarks for Data-Driven NetHack

**arXiv ID:** 2306.08772
**Authors:** Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov
**Published:** 2023-06-14T22:50:25Z
**Abstract:**
NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions. One of the promising directions for a breakthrough is using pre-collected datasets similar to recent developments in robotics, recommender systems, and more under the umbrella of offline reinforcement learning (ORL). Recently, a large-scale NetHack dataset was released; while it was a necessary step forward, it has yet to gain wide adoption in the ORL community. In this work, we argue that there are three major obstacles for adoption: resource-wise, implementation-wise, and benchmark-wise. To address them, we develop an open-source library that provides workflow fundamentals familiar to the ORL community: pre-defined D4RL-style tasks, uncluttered baseline implementations, and reliable evaluation tools with accompanying configs and logs synced to the cloud.

## Skill Description

This skill is generated from the arXiv paper: Katakomba: Tools and Benchmarks for Data-Driven NetHack (2306.08772).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2306.08772](http://arxiv.org/abs/2306.08772v2)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.