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.
@article{arxiv.2306.08772,
title = {Katakomba: Tools and Benchmarks for Data-Driven NetHack},
author = {Vladislav Kurenkov and Alexander Nikulin and Denis Tarasov and Sergey Kolesnikov},
journal= {arXiv preprint arXiv:2306.08772},
year = {2023}
}
Comments
Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks. Source code at https://github.com/corl-team/katakomba