{"id":13676245,"url":"https://github.com/takuseno/minerva","last_synced_at":"2025-07-13T16:06:00.388Z","repository":{"id":41162657,"uuid":"285768134","full_name":"takuseno/minerva","owner":"takuseno","description":"An out-of-the-box GUI tool for offline deep reinforcement learning","archived":false,"fork":false,"pushed_at":"2021-05-29T11:12:34.000Z","size":4461,"stargazers_count":101,"open_issues_count":2,"forks_count":10,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-06-13T01:13:11.387Z","etag":null,"topics":["deep-learning","deep-reinforcement-learning","offline-rl","pytorch"],"latest_commit_sha":null,"homepage":"https://takuseno.github.io/minerva","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/takuseno.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-08-07T07:35:57.000Z","updated_at":"2025-04-24T05:11:45.000Z","dependencies_parsed_at":"2022-09-26T17:20:54.319Z","dependency_job_id":null,"html_url":"https://github.com/takuseno/minerva","commit_stats":null,"previous_names":[],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/takuseno/minerva","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Fminerva","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Fminerva/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Fminerva/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Fminerva/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/takuseno","download_url":"https://codeload.github.com/takuseno/minerva/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Fminerva/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265087828,"owners_count":23709398,"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":["deep-learning","deep-reinforcement-learning","offline-rl","pytorch"],"created_at":"2024-08-02T13:00:20.819Z","updated_at":"2025-07-13T16:06:00.371Z","avatar_url":"https://github.com/takuseno.png","language":"JavaScript","funding_links":[],"categories":["JavaScript","Open Source Software/Implementations"],"sub_categories":["Off-Policy Evaluation and Learning: Applications"],"readme":"\u003cdiv align=\"center\"\u003e\u003cimg src=\"assets/logo.jpg\" width=\"800\"/\u003e\u003c/div\u003e\n\n# MINERVA: An out-of-the-box GUI tool for offline deep reinforcement learning\n[![PyPI version](https://badge.fury.io/py/minerva-ui.svg)](https://badge.fury.io/py/minerva-ui)\n![test](https://github.com/takuseno/minerva/workflows/test/badge.svg)\n[![Docker Cloud Build Status](https://img.shields.io/docker/cloud/build/takuseno/minerva)](https://hub.docker.com/r/takuseno/minerva)\n[![Documentation Status](https://readthedocs.org/projects/minerva-ui/badge/?version=latest)](https://minerva-ui.readthedocs.io/en/latest/?badge=latest)\n[![Maintainability](https://api.codeclimate.com/v1/badges/0573d1557dcc6a4321f5/maintainability)](https://codeclimate.com/github/takuseno/minerva/maintainability)\n[![codecov](https://codecov.io/gh/takuseno/minerva/branch/master/graph/badge.svg?token=7OL530W7T4)](https://codecov.io/gh/takuseno/minerva)\n![MIT](https://img.shields.io/badge/license-MIT-blue)\n\nMINERVA is an out-of-the-box GUI tool for offline deep reinforcement\nlearning, designed for everyone including non-programmers to do reinforcement\nlearning as a tool.\n\n\u003cdiv align=\"center\"\u003e\u003cimg src=\"assets/screenshot1.jpg\" width=\"800\"/\u003e\u003c/div\u003e\n\nDocumentation: https://minerva-ui.readthedocs.io\n\nChat: [![Gitter](https://img.shields.io/gitter/room/d3rlpy/minerva)](https://gitter.im/d3rlpy/minerva)\n\n## key features\n### :zap: All You Need Is Dataset\nMINERVA only requires datasets to start offline deep reinforcement learning.\nAny combinations of vector observations and image observations with discrete\nactions and continuous actions are supported.\n\n### :beginner: Stunning GUI\nMINERVA provides designed with intuitive GUI to let everyone lerverage extremely\npowerful algorithms without barriers. The GUI is developed as a Single Page\nApplication (SPA) to make it work in the eye-opening speed.\n\n### :rocket: Powerful Algorithm\nMINERVA is powered by [d3rlpy](https://github.com/takuseno/d3rlpy), a powerful\noffline deep reinforcement learning library for Python, to provide\nextremely powerful algorithms in an out-of-the-box way. The trained policy can\nbe exported as [TorchScript](https://pytorch.org/docs/stable/jit.html) and\n[ONNX](https://onnx.ai/).\n\n## installation\n### PyPI\n```\n$ pip install minerva-ui\n```\n\n### Docker\n```\n$ docker run -d --gpus all -p 9000:9000 --name minerva takuseno/minerva:latest\n```\n\n## update guide\n\nIf you update MINERVA, the database schema should be also updated as follows:\n```\n$ pip install -U minerva-ui\n$ minerva upgrade-db\n```\n\n## usage\n### run server\nAt the first time, `~/.minerva` will be automatically created to store\ndatabase, uploaded datasets and training metrics.\n```\n$ minerva run\n```\nBy default, you can access to MINERVA interface at http://localhost:9000 .\nYou can change the host and port with `--host` and `--port` arguments\nrespectively.\n\n### delete data\nYou can delete entire data (`~/.minerva`) as follows:\n```\n$ minerva clean\n```\n\n## contributions\n### build\n```\n$ npm install\n$ npm run build\n```\n\n### coding style\nThis repository is fully formatted with [yapf](https://github.com/google/yapf)\nand [standard](https://github.com/standard/standard).\nYou can format the entire scripts as follows:\n```\n$ ./scripts/format\n```\n\n### lint\nThis repository is fully analyzed with [Pylint](https://github.com/PyCQA/pylint),\n[ESLint](https://github.com/eslint/eslint) and [sass-lint](https://github.com/sasstools/sass-lint).\nYou can run analysis as follows:\n```\n$ ./scripts/lint\n```\n\n### test\nThe unit tests are provided as much as possible.\nThis repository is using `pytest-cov` instead of `pytest`.\nYou can run the entire tests as follows:\n```\n$ ./scripts/test\n```\n\n## acknowledgement\nThis work is supported by Information-technology Promotion Agency, Japan\n(IPA), Exploratory IT Human Resources Project (MITOU Program) in the fiscal\nyear 2020.\n\nThe concept of the GUI software for deep reinforcement learning is inspired by\n[DeepAnalyzer](https://ghelia.com/en/product/) from Ghelia inc.\nI'm showing the great respect to the team here.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftakuseno%2Fminerva","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftakuseno%2Fminerva","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftakuseno%2Fminerva/lists"}