{"id":13834861,"url":"https://github.com/alessiodm/drl-zh","last_synced_at":"2025-05-15T12:07:00.012Z","repository":{"id":228455188,"uuid":"741616456","full_name":"alessiodm/drl-zh","owner":"alessiodm","description":"Deep Reinforcement Learning: Zero to Hero!","archived":false,"fork":false,"pushed_at":"2024-08-18T22:11:22.000Z","size":14706,"stargazers_count":2055,"open_issues_count":1,"forks_count":78,"subscribers_count":11,"default_branch":"main","last_synced_at":"2025-04-11T21:49:07.732Z","etag":null,"topics":["deep-learning","deep-reinforcement-learning","machine-learning","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/alessiodm.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":"2024-01-10T18:59:31.000Z","updated_at":"2025-04-07T06:34:09.000Z","dependencies_parsed_at":"2024-11-20T21:35:41.292Z","dependency_job_id":null,"html_url":"https://github.com/alessiodm/drl-zh","commit_stats":null,"previous_names":["alessiodm/drl-zh"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiodm%2Fdrl-zh","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiodm%2Fdrl-zh/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiodm%2Fdrl-zh/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiodm%2Fdrl-zh/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alessiodm","download_url":"https://codeload.github.com/alessiodm/drl-zh/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254337614,"owners_count":22054254,"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","machine-learning","reinforcement-learning"],"created_at":"2024-08-04T14:00:53.123Z","updated_at":"2025-05-15T12:06:54.999Z","avatar_url":"https://github.com/alessiodm.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","AI"],"sub_categories":["Machine Learning"],"readme":"# Deep Reinforcement Learning: Zero to Hero!\n\nWelcome to the most hands-on reinforcement learning experience!\n\nThis is a short and practical introductory course on foundational and classic deep reinforcement\nlearning algorithms. By the end of the course, you will have written from scratch algorithms like\nDQN, SAC, PPO, as well as understood at a high-level the theory behind them.\n\nWe will be able to train an AI to play Atari games and land on the Moon!\n\n\u003cdiv style=\"width: 25%\"\u003e\n  \u003cimg src=\"assets/landing.gif\"\u003e\n\u003c/div\u003e\n\n## Environment Setup\n\nTo make sure we can focus on learning, the environment setup is _opinionated_ 😊 Here it is:\n\n * Install [Miniconda](https://docs.anaconda.com/free/miniconda/)\u003cbr\u003e\n   \u003csmall\u003e\n    Why conda? Because it's a full environment manager, and we can choose the Python version too.\n   \u003c/small\u003e\n * Checkout this Git repository, and `cd` into its folder.\n * Create and activate the `drlzh` virtual environment:\n    \n    ```sh\n    conda create --name drlzh python=3.11\n    conda activate drlzh\n    ```\n * Install [Poetry](https://python-poetry.org/) and install dependencies:\u003cbr\u003e\n   \u003csmall\u003e\n    Dependencies include `gymnasium[accept-rom-license]` for Atari. Make sure to accept the\n    license agreement when installing the dependencies of the project via Poetry.\n   \u003c/small\u003e\n\n   ```\n   pip install poetry\n   poetry install\n   ```\n * Install [Visual Studio Code](https://code.visualstudio.com/)\n\n## How Do I Start?\n\nOpen this repository folder in Visual Studio Code (make sure to keep the `.vscode` folder for\nsettings consistency, running on Jupyter might require some tweaks to code and imports).\n\nOpen the first `00_Intro.ipynb` notebook in Visual Studio Code, and follow along! Your objective\nis to write code in the `TODO` sections and try out the algorithms! You might even encounter some\nunit tests to verify your implementation along the way! Keep moving from one notebook to the next,\nand if you get stuck feel free to check the `/solution` folder where the full code is available.\n\nFor an expanded treatment and step-by-step coding, stay tuned for the upcoming YouTube videos!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falessiodm%2Fdrl-zh","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falessiodm%2Fdrl-zh","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falessiodm%2Fdrl-zh/lists"}