{ "info": { "author": "HendrikPN", "author_email": "hendrik.poulsen-nautrup@uibk.ac.at", "bugtrack_url": null, "classifiers": [], "description": "**Status:** Development (expect bug fixes, minor updates and new\nenvironments)\n\n\n \n\n\n# SciGym\n\n\n \n\n\n**SciGym is a curated library for reinforcement learning environments in science.**\nThis is the `scigym` open-source library which gives you access to a standardized set of science environments.\nVisit our webpage at [scigym.ai]. This website serves as a open-source database for science environments: A port where science and reinforcement learning meet.\n\n\n \n\n\n[See What's New section below](#whats-new)\n\n## Basics\n\nThis project is in line with the policies of the [OpenAI gym]:\n\nThere are two basic concepts in reinforcement learning: the environment\n(namely, the outside world) and the agent (namely, the algorithm you are\nwriting). The agent sends `actions` to the environment, and\nthe environment replies with `observations` and\n`rewards` (that is, a score).\n\nThe core `gym` interface is [Env], which is the unified\nenvironment interface. There is no interface for agents; that part is\nleft to you. The following are the `Env` methods you should know:\n\n* `reset(self)`: Reset the environment's state. Returns `observation`.\n* `step(self, action)`: Step the environment by one timestep. Returns `observation`, `reward`, `done`, `info`.\n* `render(self, mode='human', close=False)`: Render one frame of the environment. The default mode will do something human friendly, such as pop up a window. Passing the `close` flag signals the renderer to close any such windows.\n\n## Installation\n\nThere are two main options for the installation of `scigym`:\n\n#### (a) minimal install (recommended)\n\nThis method allows you to install the package with no environment specific dependencies, and later add the dependencies for specific environments as you need them.\n\nYou can perform a minimal install of `scigym` with:\n\n ```sh\n pip install scigym\n ```\nor\n ```sh\n git clone https://github.com/hendrikpn/scigym.git\n cd scigym\n pip install -e .\n ```\n\nTo later add the dependencies for a particular `environment_name`, run the following command:\n\n ```sh\n pip install scigym[environment_name]\n ```\nor from the folder containing `setup.py`\n ```sh\n pip install -e .[environment_name]\n ```\n\n#### (b) full install\n\nThis method allows you to install the package, along with all dependencies required for all environments. Be careful, scigym is growing, and this method may install a large number of packages. To view all packages that will be installed during a full install, see the `requirements.txt` file in the root directory. If you wish to perform a full installation you can run:\n\n ```sh\n pip install scigym['all']\n ```\nor\n ```sh\n git clone https://github.com/hendrikpn/scigym.git\n cd scigym\n pip install -e .['all']\n ```\n\n## Available Environments\n\nAt this point we have the following environments available for you to play with:\n\n- [`surfacecode-decoding`](https://github.com/HendrikPN/scigym/tree/master/scigym/envs/quantum_physics/quantum_computing/surfacecode_decoding)\n- [`teleportation`](https://github.com/HendrikPN/scigym/tree/master/scigym/envs/quantum_physics/quantum_computing/teleportation)\n\n## What's New\n\n- 2019-08-30 This is `scigym` version 0.0.2!\n- 2019-08-30 `scigym` is now available as a package on [PyPI](https://pypi.org/project/scigym/).\n- 2019-08-06 Added [Travis-CI](https://travis-ci.org/HendrikPN/scigym).\n- 2019-08-06: Added [teleportation](https://github.com/HendrikPN/scigym/tree/master/scigym/envs/quantum_physics/quantum_computing/teleportation) environment.\n- 2019-07-21: Added standardized unit testing for all scigym environments.\n- 2019-03-04: Added surfacecode environment.\n- 2019-02-09: Initial commit. Hello world :)\n\n [image]: https://img.shields.io/badge/Supported%20By-UNITARY%20FUND-brightgreen.svg?style=for-the-badge\n [OpenAI gym]: https://github.com/openai/gym\n [scigym.ai]: https://scigym.ai\n [Env]: https://github.com/openai/gym/blob/master/gym/core.py", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/HendrikPN/scigym", "keywords": "", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "scigym", "package_url": "https://pypi.org/project/scigym/", "platform": "", "project_url": "https://pypi.org/project/scigym/", "project_urls": { "Homepage": "https://github.com/HendrikPN/scigym" }, "release_url": "https://pypi.org/project/scigym/0.0.2/", "requires_dist": null, "requires_python": "", "summary": "SciGym -- The OpenAI Gym for Science: A platform for your scientific reinforcement learning problem.", "version": "0.0.2" }, "last_serial": 5760933, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "efb4c794d6a1755d736abfa028bbc365", "sha256": "8f1e16908f70110f655f7971a63f90af4e15d9a8c842878f4018db2612ed9198" }, "downloads": -1, "filename": "scigym-0.0.1.tar.gz", "has_sig": false, "md5_digest": "efb4c794d6a1755d736abfa028bbc365", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13550374, "upload_time": "2019-08-30T12:51:03", "url": "https://files.pythonhosted.org/packages/5c/fb/f87dadbd7f71c5f12dbea3e1bd77270f32f526849124be4366c6ca1f57fd/scigym-0.0.1.tar.gz" } ], "0.0.2": [ { "comment_text": "", "digests": { "md5": "b10f5760f43fa0ebc7013de1c834d95e", "sha256": "66802bc21a01d1bc7c87e39c90adc40328f545e8188aec219d291eb24505eb1b" }, "downloads": -1, "filename": "scigym-0.0.2.tar.gz", "has_sig": false, "md5_digest": "b10f5760f43fa0ebc7013de1c834d95e", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13552686, "upload_time": "2019-08-30T15:46:43", "url": "https://files.pythonhosted.org/packages/33/92/9f3beabf17d0ceb6a84c7b383f2e504d3614bba8a9e72434270d715fb46b/scigym-0.0.2.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "b10f5760f43fa0ebc7013de1c834d95e", "sha256": "66802bc21a01d1bc7c87e39c90adc40328f545e8188aec219d291eb24505eb1b" }, "downloads": -1, "filename": "scigym-0.0.2.tar.gz", "has_sig": false, "md5_digest": "b10f5760f43fa0ebc7013de1c834d95e", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 13552686, "upload_time": "2019-08-30T15:46:43", "url": "https://files.pythonhosted.org/packages/33/92/9f3beabf17d0ceb6a84c7b383f2e504d3614bba8a9e72434270d715fb46b/scigym-0.0.2.tar.gz" } ] }