Dungeons and Data: A Large-Scale NetHack Dataset

Eric Hambro · Roberta Raileanu · Danielle Rothermel · Vegard Mella · Tim Rocktäschel · Heinrich Küttler · Naila Murray

Hall J #1028

Keywords: [ RL dataset ] [ human demonstrations ] [ offline RL ] [ Reinforcement Learning ] [ Procedural Generation ]

[ Abstract ]
[ Paper [ Poster [ OpenReview
Thu 1 Dec 2 p.m. PST — 4 p.m. PST


Recent breakthroughs in the development of agents to solve challenging sequential decision making problems such as Go, StarCraft, or DOTA, have relied on both simulated environments and large-scale datasets. However, progress on this research has been hindered by the scarcity of open-sourced datasets and the prohibitive computational cost to work with them. Here we present the NetHack Learning Dataset (NLD), a large and highly-scalable dataset of trajectories from the popular game of NetHack, which is both extremely challenging for current methods and very fast to run. NLD consists of three parts: 10 billion state transitions from 1.5 million human trajectories collected on the NAO public NetHack server from 2009 to 2020; 3 billion state-action-score transitions from 100,000 trajectories collected from the symbolic bot winner of the NetHack Challenge 2021; and, accompanying code for users to record, load and stream any collection of such trajectories in a highly compressed form. We evaluate a wide range of existing algorithms for learning from demonstrations, showing that significant research advances are needed to fully leverage large-scale datasets for challenging sequential decision making tasks.

Chat is not available.