{"id":13528592,"url":"https://github.com/minerllabs/minerl","last_synced_at":"2025-12-14T19:45:05.688Z","repository":{"id":37271443,"uuid":"183058962","full_name":"minerllabs/minerl","owner":"minerllabs","description":"MineRL Competition for Sample Efficient Reinforcement Learning - Python Package","archived":false,"fork":false,"pushed_at":"2025-01-22T20:22:41.000Z","size":118723,"stargazers_count":768,"open_issues_count":234,"forks_count":159,"subscribers_count":18,"default_branch":"dev","last_synced_at":"2025-03-29T06:13:27.334Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://minerl.io/docs/","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/minerllabs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-04-23T16:55:21.000Z","updated_at":"2025-03-28T03:41:28.000Z","dependencies_parsed_at":"2023-02-10T05:45:20.701Z","dependency_job_id":"864400c1-d25c-478c-9598-372e9d702571","html_url":"https://github.com/minerllabs/minerl","commit_stats":{"total_commits":719,"total_committers":45,"mean_commits":"15.977777777777778","dds":0.611961057023644,"last_synced_commit":"123fadc3b426a7c5f3b22e9283df52037e0dd66f"},"previous_names":[],"tags_count":11,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minerllabs%2Fminerl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minerllabs%2Fminerl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minerllabs%2Fminerl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minerllabs%2Fminerl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/minerllabs","download_url":"https://codeload.github.com/minerllabs/minerl/tar.gz/refs/heads/dev","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246655200,"owners_count":20812597,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-01T07:00:21.594Z","updated_at":"2025-12-14T19:45:05.683Z","avatar_url":"https://github.com/minerllabs.png","language":"Java","funding_links":[],"categories":["Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL)","Environments","Papers","时间序列","Java"],"sub_categories":["RL/DRL Environments","NeurIPS 2022","网络服务_其他","NeurIPS 2023"],"readme":"# The [MineRL](http://minerl.io) Python Package\n\n[![Documentation Status](https://readthedocs.org/projects/minerl/badge/?version=latest)](https://minerl.readthedocs.io/en/latest/?badge=latest)\n[![Downloads](https://pepy.tech/badge/minerl)](https://pepy.tech/project/minerl)\n[![PyPI version](https://badge.fury.io/py/minerl.svg)](https://badge.fury.io/py/minerl)\n[![\"Open Issues\"](https://img.shields.io/github/issues-raw/minerllabs/minerl.svg)](https://github.com/minerllabs/minerl/issues)\n[![GitHub issues by-label](https://img.shields.io/github/issues/minerllabs/minerl/bug.svg?color=red)](https://github.com/minerllabs/minerl/issues?utf8=%E2%9C%93\u0026q=is%3Aissue+is%3Aopen+label%3Abug)\n[![Discord](https://img.shields.io/discord/565639094860775436.svg?label=\u0026logo=discord\u0026logoColor=ffffff\u0026color=7389D8\u0026labelColor=6A7EC2)](https://discord.gg/BT9uegr)\n\nPython package providing easy to use Gym environments and data access for training agents in Minecraft.\n\nCurious to see what people have done with MineRL? See [this page where we collect projects using MineRL](https://minerl.readthedocs.io/en/latest/notes/useful-links.html). **Got a project using MineRL (academic or fun hobby project)?** Edit [this file](https://github.com/minerllabs/minerl/blob/dev/docs/source/notes/useful-links.rst), add links to your projects and create a PR!\n\nTo get started with MineRL, [check out the docs here](https://minerl.readthedocs.io/en/latest/)!\n\n## ⚠️Update regarding MineRL-v0 data on 17th June 2024\nThe original data mirrors for MineRL-v0 are down (e.g., original `MineRLObtainDiamond-v0` data). We have uploaded copies of the primary datasets to this Zenodo record so people can find them: https://zenodo.org/records/12659939\n\n## MineRL Versions\n\nMineRL consists of three unique versions, each with a slightly different sets of features. See full comparison [here](https://minerl.readthedocs.io/en/v1.0.0/notes/versions.html).\n\n* v1.0: [[Code](https://github.com/minerllabs/minerl)][[Docs](https://minerl.readthedocs.io/en/latest/)]\n  This version you are looking at. Needed for the [OpenAI VPT](https://github.com/openai/Video-Pre-Training) models and the [MineRL BASALT 2022](https://www.aicrowd.com/challenges/neurips-2022-minerl-basalt-competition) competition.\n* v0.4: [[Code](https://github.com/minerllabs/minerl/tree/v0.4)][[Docs](https://minerl.readthedocs.io/en/v0.4.4/)]\n  Version used in the 2021 competitions (Diamond and BASALT). Supports the original [MineRL-v0 dataset](https://arxiv.org/abs/1907.13440). Install with `pip install minerl==0.4.4`\n* v0.3: [[Code](https://github.com/minerllabs/minerl/tree/pypi_0.3.7)][[Docs](https://minerl.readthedocs.io/en/v0.3.7/)]\n  Version used prior to 2021, including the first two MineRL competitions (2019 and 2020). Supports the original [MineRL-v0 dataset](https://arxiv.org/abs/1907.13440). Install with `pip install minerl==0.3.7`\n\n## Installation\n\nInstall [requirements](https://minerl.readthedocs.io/en/latest/tutorials/index.html) (Java JDK 8 is **required**. Mac may require [additional steps](https://github.com/minerllabs/minerl/issues/659#issuecomment-1306635414)) and then install MineRL with\n```\npip install git+https://github.com/minerllabs/minerl\n```\n\n## Basic Usage\n\nCan be used much like any Gym environment:\n\n```python\nimport gym\nimport minerl\n\n# Uncomment to see more logs of the MineRL launch\n# import coloredlogs\n# coloredlogs.install(logging.DEBUG)\n\nenv = gym.make(\"MineRLBasaltBuildVillageHouse-v0\")\nobs = env.reset()\n\ndone = False\nwhile not done:\n    ac = env.action_space.noop()\n    # Spin around to see what is around us\n    ac[\"camera\"] = [0, 3]\n    obs, reward, done, info = env.step(ac)\n    env.render()\nenv.close()\n```\n\nCheck the [documentation](https://minerl.readthedocs.io/en/latest) for further examples and notes.\n\n## Major changes in v1.0\n\n- New Minecraft version (11.2 -\u003e 16.5)\n- Larger resolution by default (64x64 -\u003e 640x360)\n- Near-human action-space: no more `craft` and `smelt` actions. Only GUI and mouse control (camera action moves mouse around).\n- Observation space is only pixels, no more inventory observation by default.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminerllabs%2Fminerl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fminerllabs%2Fminerl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminerllabs%2Fminerl/lists"}