BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks: Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Datasets and Benchmarks Track

Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Rohin Shah

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

1 Citation (SciVal)

Abstract

The MineRL BASALT competition has served to catalyze advances in learning from human feedback through four hard-to-specify tasks in Minecraft, such as create and photograph a waterfall. Given the completion of two years of BASALT competitions, we offer to the community a formalized benchmark through the BASALT Evaluation and Demonstrations Dataset (BEDD), which serves as a resource for algorithm development and performance assessment. BEDD consists of a collection of 26 million image-action pairs from nearly 14, 000 videos of human players completing the BASALT tasks in Minecraft. It also includes over 3, 000 dense pairwise human evaluations of human and algorithmic agents. These comparisons serve as a fixed, preliminary leaderboard for evaluating newly-developed algorithms. To enable this comparison, we present a streamlined codebase for benchmarking new algorithms against the leaderboard. In addition to presenting these datasets, we conduct a detailed analysis of the data from both datasets to guide algorithm development and evaluation. The released code and data are available at https://github.com/minerllabs/basalt-benchmark.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 36 (NeurIPS 2023)
Subtitle of host publicationDatasets and Benchmarks Track
Number of pages12
Volume36
ISBN (Electronic)9781713899921
Publication statusPublished - 16 Dec 2023
Event37th Conference on Neural Information Processing Systems, NeurIPS 2023 - New Orleans, USA United States
Duration: 10 Dec 202316 Dec 2023

Publication series

NameAdvances in Neural Information Processing Systems
PublisherMIT Press
ISSN (Print)1049-5258

Conference

Conference37th Conference on Neural Information Processing Systems, NeurIPS 2023
Country/TerritoryUSA United States
CityNew Orleans
Period10/12/2316/12/23

Funding

Creating these datasets and this benchmark was only possible with the help of many people and organizations. FTX Future Fund Regranting Program, Microsoft, Encultured AI, and AI Journal provided financial support for the competition and resulting data. We thank Berkeley Existential Risk Initiative (BERI) for the support in organizing the BASALT competition. Karolis Ramanauskas was supported by the UKRI Centre for Doctoral Training in Accountable, Responsible and Transparent AI (ART-AI) [EP/S023437/1] and the University of Bath. We thank our amazing advisory board of the 2022 competition - Fei Fang, Kiant\u00E9 Brantley, Andrew Critch, Sam Devlin, and Oriol Vinyals - for their advice and guidance. We also thank any previous organizers or advisors of the previous competitions for their contributions. Finally, we thank AIcrowd for their help hosting the competion and the MTurk workers for their work evaluating the submissions.

FundersFunder number
UK Research and InnovationEP/S023437/1

    ASJC Scopus subject areas

    • Computer Networks and Communications
    • Information Systems
    • Signal Processing

    Fingerprint

    Dive into the research topics of 'BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks: Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Datasets and Benchmarks Track'. Together they form a unique fingerprint.

    Cite this