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

Stephanie Milani, A. Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton +26 more
2/12/2026

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment

84% match1 repo82026

Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models

82% match1 repo32024

RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback

82% match2026

BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks

82% match1 repo222026

Learning Reward for Robot Skills Using Large Language Models via Self-Alignment

81% match1 repo192026

CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment

81% match1 repo22024

Cite this paper

@article{milani2026towards,
  title  = {Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition},
  author = {Stephanie Milani and A. Kanervisto and Karolis Ramanauskas and Sander Schulhoff and Brandon Houghton and S. Mohanty and Byron V. Galbraith and Ke Chen and Yan Song and Tianze Zhou and Bingquan Yu and He Liu and Kai Guan and Yujing Hu and Tangjie Lv and Federico Malato and Florian Leopold and Amogh Raut and Ville Hautamaki and Andrew Melnik and Shu Ishida and João F. Henriques and Robert Klassert and Walter Laurito and Nicholas Popovic and Ellen R. Novoseller and Vinicius G. Goecks and Nicholas R. Waytowich and David Watkins and J. Miller and Rohin Shah},
  year   = {2026},
  eprint = {2303.13512},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/pdf/2303.13512},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.13512.svg)](https://codeofpaper.com/paper/2303.13512)

Discussion