Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
- Stephanie Milani ,
- Anssi Kanervisto ,
- Karolis Ramanauskas ,
- Sander Schulhoff ,
- Brandon Houghton ,
- S. Mohanty ,
- Byron V. Galbraith ,
- Ke Chen ,
- Yan Song ,
- Tianze Zhou ,
- Bingquan Yu ,
- He Liu ,
- Kai Guan ,
- Yujing Hu ,
- Tangjie Lv ,
- Federico Malato ,
- Florian Leopold ,
- Amogh Raut ,
- Ville Hautamaki ,
- Andrew Melnik ,
- Shu Ishida ,
- João F. Henriques ,
- Robert Klassert ,
- Walter Laurito ,
- Ellen R. Novoseller ,
- Vinicius G. Goecks ,
- Nicholas R. Waytowich ,
- David Watkins ,
- J. Miller ,
- Rohin Shah
Machine Learning Research |
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022. The BASALT challenge asks teams to compete to develop algorithms to solve tasks with hard-to-specify reward functions in Minecraft. Through this competition, we aimed to promote the development of algorithms that use human feedback as channels to learn the desired behavior. We describe the competition and provide an overview of the top solutions. We conclude by discussing the impact of the competition and future directions for improvement.
2023 S. Milani et al.