百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
P

Plan4MC

> 编程语言
开源

[NeurIPS 2023 FMDM 研讨会] 开放世界长期任务的技能强化学习和规划

200 stars0 点赞1 次浏览
访问官网GitHub

工具介绍

[NeurIPS 2023 FMDM 研讨会] 开放世界长期任务的技能强化学习和规划

Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks

Plan4MC is a multi-task agent in Minecraft, solving long-term tasks via planning over basic skills. It acquire three types of fine-grained basic skills through reinforcement learning without demonstrations. With a skill graph pre-generated by the Large Language Model, the skill search algorithm generates skill plans and interactively selects policies to solve complicated tasks. Plan4MC accomplishes 24 diverse hard tasks in Minecraft.

Installation

  • Install MineDojo environment following the official document. It requires python >= 3.9. We install jdk 1.8.0_171.

  • Upgrade the MineDojo package:

    • Delete the original package pip uninstall minedojo.
    • Download our modified MineDojo. Run python setup.py install.
    • To this end, you can successfully run validate_install.py here.
  • Install python packages in requirements.txt. Note that we require PyTorch>=1.8.1 and x-transformers==0.27.1.

  • Download the pretrained MineCLIP model named attn.pth. Move the file to mineclip_official/.

Tasks

  • We provide 24 diverse tasks configured in envs/hard_task_conf.yaml. To create an environment for a task:
…
  • To generate task names, initial plans and involved skills for all the tasks, run python plan_all_tasks.py.

Plan4MC

  • Pre-trained models for skills are released in skills/models/.

  • To test Plan4MC on the task 'get_furnace_nearby_with_logs' as an example, run python test.py --task get_furnace_nearby_with_logs. Arguments:

    --task: available tasks are listed in envs/hard_task_conf.yaml.

    --save-path: output directory for testing results.

    --test-episode: number of testing episodes.

    --save-gif: set to 1 to save testing videos.

Citation

bibtex
@article{yuan2023plan4mc,
      title={{Plan4MC}: Skill Reinforcement Learning and Planning for Open-World {Minecraft} Tasks}, 
      author={Yuan, Haoqi and Zhang, Chi and Wang, Hongcheng and Xie, Feiyang and Cai, Penglin and Dong, Hao and Lu, Zongqing},
      journal={arXiv preprint arXiv:2303.16563},
      year={2023},
}

Issues· 4 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Python

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月18日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言