Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

Approved

Classifications

MinEdu publication type
A4 Article in conference proceedings (peer-reviewed)
Definition
Article
Target group
Scientific
Peer reviewed
Peer-reviewed
Article type
Other article
Host publication type
Conference platform

Authors of the publication

Number of authors
34
Authors
Milani, Stephanie; Kanervisto, Anssi; Ramanauskas, Karolis; Schulhoff, Sander; Houghton, Brandon; Mohanty, Sharada; Galbraith, Byron; Chen, Ke; Song, Yan; Zhou, Tianze; Yu, Bingquan; Liu, He; Guan, Kai; Hu, Yujing; Lv, Tangjie; Malato, Federico; Leopold, Florian; Raut, Amogh; Hautamäki, Ville; Melnik, Andrew; Ishida, Shu; Henriques, João F.; Klassert, Robert; Laurito, Walter; Cazzonelli, Lucas; Kulbach, Cedric; Popovic, Nicholas; Schweizer, Marvin; Novoseller, Ellen; Goecks, Vinicius G; Waytowich, Nicholas; Watkins, David; Miller, Josh; Shah, Rohin
Local authors
Author
Malato, Federico
Unit
School of Computing
Unit
School of Computing

Publication channel information

Title of host publication
Proceedings of Machine Learning Research
Editors of host publication
Ciccone, Marco; Stolovitzky, Gustavo; Albrecht, Jacob
Name of conference
Annual Conference on Neural Information Processing Systems
Title of journal/series
Proceedings of Machine Learning Research
ISSN (electronic)
2640-3498
ISSN (linking)
2640-3498
Publication forum ID
87561
Publication forum level
1
Internationality
Yes

Detailed publication information

Publication year
2023
Reporting year
2023
Journal/series volume number
220
Page numbers
171-188
Language of publication
English

Co-publication information

International co-publication
Yes
Co-publication with a company
Yes

Classification and additional information

MinEdu field of science classification
113 Computer and information sciences
Keywords
fine-tuning; imitation learning; Learning from humans; preference learning; reinforcement learning from human feedback; reward modeling

Source database ID

Scopus ID
2-s2.0-85179129024