Dungeons and Data: A Large-Scale NetHack Dataset

• URL: http://arxiv.org/abs/2211.00539v3
• Date: Fri, 24 Nov 2023 16:27:22 GMT
• Title: Dungeons and Data: A Large-Scale NetHack Dataset
• Authors: Eric Hambro, Roberta Raileanu, Danielle Rothermel, Vegard Mella, Tim Rockt\"aschel, Heinrich K\"uttler, Naila Murray
• Abstract summary: We present the NetHack Learning dataset (NLD), a large and highly-scalable dataset of trajectories from the popular game of NetHack. 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. We evaluate a wide range of existing algorithms including online and offline RL, as well as learning from demonstrations, showing that significant research advances are needed to fully leverage large-scale datasets for challenging sequential
• Score: 19.5560914918284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 including online and offline RL, as well as learning from demonstrations, showing that significant research advances are needed to fully leverage large-scale datasets for challenging sequential decision making tasks.

Related papers

• D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning [99.33607114541861]
  We propose a new benchmark for offline RL that focuses on realistic simulations of robotic manipulation and locomotion environments. Our proposed benchmark covers state-based and image-based domains, and supports both offline RL and online fine-tuning evaluation.
  arXiv  Detail & Related papers  (2024-08-15T22:27:00Z)
• Katakomba: Tools and Benchmarks for Data-Driven NetHack [52.0035089982277]
  NetHack is known as the frontier of reinforcement learning research. We argue that there are three major obstacles for adoption: resource-wise, implementation-wise, and benchmark-wise. We develop an open-source library that provides workflow fundamentals familiar to the offline reinforcement learning community.
  arXiv  Detail & Related papers  (2023-06-14T22:50:25Z)
• NetHack is Hard to Hack [37.24009814390211]
  In the NeurIPS 2021 NetHack Challenge, symbolic agents outperformed neural approaches by over four times in median game score. We present an extensive study on neural policy learning for NetHack. We produce a state-of-the-art neural agent that surpasses previous fully neural policies by 127% in offline settings and 25% in online settings on median game score.
  arXiv  Detail & Related papers  (2023-05-30T17:30:17Z)
• Dataset Distillation: A Comprehensive Review [76.26276286545284]
  dataset distillation (DD) aims to derive a much smaller dataset containing synthetic samples, based on which the trained models yield performance comparable with those trained on the original dataset. This paper gives a comprehensive review and summary of recent advances in DD and its application.
  arXiv  Detail & Related papers  (2023-01-17T17:03:28Z)
• Insights From the NeurIPS 2021 NetHack Challenge [40.52602443114554]
  The first NeurIPS 2021 NetHack Challenge showcased community-driven progress in AI. It served as a direct comparison between neural (e.g., deep RL) and symbolic AI, as well as hybrid systems. No agent got close to winning the game, illustrating NetHack's suitability as a long-term benchmark for AI research.
  arXiv  Detail & Related papers  (2022-03-22T17:01:07Z)
• LID 2020: The Learning from Imperfect Data Challenge Results [242.86700551532272]
  Learning from Imperfect Data workshop aims to inspire and facilitate the research in developing novel approaches. We organize three challenges to find the state-of-the-art approaches in weakly supervised learning setting. This technical report summarizes the highlights from the challenge.
  arXiv  Detail & Related papers  (2020-10-17T13:06:12Z)
• 2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework [57.847010327319964]
  We propose a data-efficient framework that can train the model from scratch on small datasets. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D neural network-based two-stream framework. It is proved that our method can achieve a promising result even without a pre-trained model on large scale datasets.
  arXiv  Detail & Related papers  (2020-08-10T09:50:28Z)
• The NetHack Learning Environment [79.06395964379107]
  We present the NetHack Learning Environment (NLE), a procedurally generated rogue-like environment for Reinforcement Learning research. We argue that NetHack is sufficiently complex to drive long-term research on problems such as exploration, planning, skill acquisition, and language-conditioned RL. We demonstrate empirical success for early stages of the game using a distributed Deep RL baseline and Random Network Distillation exploration.
  arXiv  Detail & Related papers  (2020-06-24T14:12:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.