Abstract
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.
Abstract (translated)
为促进从人类反馈中 fine-tuning 基础模型的研究,我们在 NeurIPS 2022 年举办了 MineRL BASALT 比赛,比赛的主题是从人类反馈中 fine-tuning 基础模型。BASALT 挑战要求团队竞争,开发用于解决 Minecraft 中难以定义奖励函数的任务的算法。通过这场比赛,我们旨在促进使用人类反馈作为学习目标行为的算法开发。我们描述了比赛,并概述了最优秀的解决方案。最后,我们讨论了比赛的影响和未来的改进方向。
URL
https://arxiv.org/abs/2303.13512