{"id":24510804,"url":"https://github.com/rhdeck/keras-reinforcement-learning-notebook","last_synced_at":"2025-03-15T09:41:40.545Z","repository":{"id":104234096,"uuid":"114359970","full_name":"rhdeck/keras-reinforcement-learning-notebook","owner":"rhdeck","description":"Refined single-file iPython notebook implementing reinforcement learning in Keras","archived":false,"fork":false,"pushed_at":"2017-12-15T10:43:48.000Z","size":7,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-22T00:35:44.394Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/rhdeck.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":"2017-12-15T10:43:44.000Z","updated_at":"2017-12-15T12:35:28.000Z","dependencies_parsed_at":null,"dependency_job_id":"515a6dc0-f6ab-49da-a4c5-4916d7e34668","html_url":"https://github.com/rhdeck/keras-reinforcement-learning-notebook","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/rhdeck%2Fkeras-reinforcement-learning-notebook","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhdeck%2Fkeras-reinforcement-learning-notebook/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhdeck%2Fkeras-reinforcement-learning-notebook/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhdeck%2Fkeras-reinforcement-learning-notebook/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rhdeck","download_url":"https://codeload.github.com/rhdeck/keras-reinforcement-learning-notebook/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243713403,"owners_count":20335566,"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":"2025-01-22T00:31:17.833Z","updated_at":"2025-03-15T09:41:40.513Z","avatar_url":"https://github.com/rhdeck.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# keras-reinforcement-learning-notebook\n# Prerequisites\n1. Your preferred iPython notebook system (I like [Jupyter](https://www.google.com/url?sa=t\u0026rct=j\u0026q=\u0026esrc=s\u0026source=web\u0026cd=1\u0026cad=rja\u0026uact=8\u0026ved=0ahUKEwju05ie6YvYAhWCyyYKHWBXAIgQFggpMAA\u0026url=http%3A%2F%2Fjupyter.org%2F\u0026usg=AOvVaw2BGkfjMHm2Y7GNO_mDEeDH), which I installed on windows via [Anaconda](https://www.anaconda.com/download/))\n2. Key `pip install`:\n   * tensorflow (recommend gpu build)\n   * keras\n   * tqdm\n3. Recommended: CuDNN 8.0 from NVidia to get GPU performance.  \n# Installation\n```\ngit clone rhdeck/keras-reinforcement-learning-notebook\ncd keras-reinforcement-learning-notebook\njupyter notebook\n```\nAnd:\n* (from browser) Run all Cells\n\nKey things to watch:\n1. The training process shows its overall accuracy. Watch it get better over time. \n2. The testing process shows the game being played. This is slow, but very cool.\n\nAll credit to @EderSantana for his [article](http://edersantana.github.io/articles/keras_rl/) and useful [gist](https://gist.github.com/EderSantana/c7222daa328f0e885093). This repository reflects my investigations and cleanup to make iPython-based investigation of his findings just a little easier. \n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frhdeck%2Fkeras-reinforcement-learning-notebook","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frhdeck%2Fkeras-reinforcement-learning-notebook","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frhdeck%2Fkeras-reinforcement-learning-notebook/lists"}