Timezone: »

 
Poster
Dungeons and Data: A Large-Scale NetHack Dataset
Eric Hambro · Roberta Raileanu · Danielle Rothermel · Vegard Mella · Tim Rocktäschel · Heinrich Küttler · Naila Murray

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #1028
in Poster Session 6 »

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.

Keywords: Reinforcement Learning · offline RL · Procedural Generation · human demonstrations · RL dataset
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Eric Hambro (Facebook AI Research)
Roberta Raileanu (FAIR)
Danielle Rothermel (NYU)
Vegard Mella (Facebook AI Research)
Tim Rocktäschel (University College London, Facebook AI Research)

Tim is a Researcher at Facebook AI Research (FAIR) London, an Associate Professor at the Centre for Artificial Intelligence in the Department of Computer Science at University College London (UCL), and a Scholar of the European Laboratory for Learning and Intelligent Systems (ELLIS). Prior to that, he was a Postdoctoral Researcher in Reinforcement Learning at the University of Oxford, a Junior Research Fellow in Computer Science at Jesus College, and a Stipendiary Lecturer in Computer Science at Hertford College. Tim obtained his Ph.D. from UCL under the supervision of Sebastian Riedel, and he was awarded a Microsoft Research Ph.D. Scholarship in 2013 and a Google Ph.D. Fellowship in 2017. His work focuses on reinforcement learning in open-ended environments that require intrinsically motivated agents capable of transferring commonsense, world and domain knowledge in order to systematically generalize to novel situations.

Heinrich Küttler (Facebook AI Research)
Naila Murray (FAIR)

More from the Same Authors