{"id":13633386,"url":"https://github.com/gomerudo/nas-env","last_synced_at":"2025-04-18T10:34:34.046Z","repository":{"id":86440576,"uuid":"177586414","full_name":"gomerudo/nas-env","owner":"gomerudo","description":"A simple OpenAI Gym environment for Neural Architecture Search (NAS)","archived":false,"fork":false,"pushed_at":"2020-05-04T22:38:59.000Z","size":203,"stargazers_count":29,"open_issues_count":0,"forks_count":3,"subscribers_count":7,"default_branch":"develop","last_synced_at":"2024-11-09T02:34:11.337Z","etag":null,"topics":["neural-architecture-search","openai-gym","reinforcement-learning"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/gomerudo.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}},"created_at":"2019-03-25T12:56:01.000Z","updated_at":"2024-02-06T03:33:08.000Z","dependencies_parsed_at":"2023-07-13T17:31:38.350Z","dependency_job_id":null,"html_url":"https://github.com/gomerudo/nas-env","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gomerudo%2Fnas-env","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gomerudo%2Fnas-env/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gomerudo%2Fnas-env/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gomerudo%2Fnas-env/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gomerudo","download_url":"https://codeload.github.com/gomerudo/nas-env/tar.gz/refs/heads/develop","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249479055,"owners_count":21279187,"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":["neural-architecture-search","openai-gym","reinforcement-learning"],"created_at":"2024-08-01T23:00:36.230Z","updated_at":"2025-04-18T10:34:33.747Z","avatar_url":"https://github.com/gomerudo.png","language":"Python","funding_links":[],"categories":["Profiling","Scheduling","AutoML","Tools and projects"],"sub_categories":["Profiling","LLM"],"readme":"# NASGym\n\nA proof-of-concept OpenAI Gym environment for Neural Architecture Search (NAS).\n\n**Under development:** The code and documentation of this repository may contain minor bugs.\n\n## Overview\n\nThis is a python package developed for the research project [Learning to reinforcement learn for Neural Architecture Search](https://arxiv.org/abs/1911.03769).\n\nThe environment is fully compatible with the OpenAI baselines. It implements the RL steps for NAS, using the Neural Structure Code (NSC) of [BlockQNN: Efficient Block-wise Neural Network Architecture Generation](https://arxiv.org/abs/1808.05584) to encode the networks and make architectural changes. Under this setting, a Neural Network (i.e. the state for the reinforcement learning agent) is modeled as a list of NSCs, an action is the addition of a layer to the network, and the reward is the accuracy after the early-stop training. The datasets considered so far are the CIFAR-10 dataset (default) and the meta-dataset (it has to be downloaded as specified in [the original repository](https://github.com/gomerudo/meta-dataset)).\n\n## Highlights\n\nThe code structure allows you to:\n\n- Set the main training variables in a config.ini file (see the [resources](resources/) directory).\n- Easily change the layers to consider and their hyperparameters in a yml file (see the [resources](resources/) directory).\n- Create customized TensorFlow estimators to plug-in your performance estimation strategy.\n- Store a local database of the experiments (CSV file by default, with an option to create your own DB interfaces).\n- Create your own dataset handlers to input the TensorFlow estimators.\n  \n## Installation\n\nThe recommended way to install the package is in editable mode:\n\n```\ncd ${GIT_STORAGE}/nas-env\ngit checkout develop\npip install -e .\n```\n## Example\n\nTo see an example of how to use this environment after installation, check the scripts in the [nas-dmlr repo](https://github.com/gomerudo/nas-dmrl).\n## Future plans\n\n- Architectural changes to the source code to ease plugging-in the different NAS elements, i.e. the performance estimation strategy and the search space.\n- Generate documentation\n- Publish the package in PiPy.\n\n## Contributing\n\nSo far I am the only contributor to this project, but I would like to improve the design to allow for even easier integration of the different NAS elements. Please feel free to join me in this quest!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgomerudo%2Fnas-env","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgomerudo%2Fnas-env","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgomerudo%2Fnas-env/lists"}