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

03/23/2023

∙

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.

READ FULL TEXT

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

Retrospective on the 2021 BASALT Competition on Learning from Human Feedback

Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification

The MineRL BASALT Competition on Learning from Human Feedback

Improving Learning-to-Defer Algorithms Through Fine-Tuning

Learning a Universal Human Prior for Dexterous Manipulation from Human Preference

Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft

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

Related Research

Retrospective on the 2021 BASALT Competition on Learning from Human Feedback

Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification

The MineRL BASALT Competition on Learning from Human Feedback

Improving Learning-to-Defer Algorithms Through Fine-Tuning

Learning a Universal Human Prior for Dexterous Manipulation from Human Preference

Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft